Note: In-development notebook.

Introduction

In this notebook, we aim at comparing various baselines approaches for Learnong to Run a Power Network. As such, we conduct several same-context experiments on four baselines solutions. The first section of this document gives insight about the context of the experiment, including the initial power grid used, and the shape of the injections. The second section defines four baselines solutions, which include a do-nothing agent, two random action models and a greedy branch disconnection agent. Finally, we infer some statistics about the performance of those models.

Please refer to the associated master thesis report (available at https://github.com/MarvinLer/L2RPN_env/blob/dev/doc/LEROUSSEAU_Marvin_report_master_thesis.pdf) for an introduction to this project.

In [1]:
%matplotlib inline

import matplotlib
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = [15, 5]
import numpy as np
import sys
import os
sys.path.append(os.path.abspath("../"))

Usage example with the game environment

This subsection is intended to display a basic usage of the proposed game environment. We constructed it on the same overall API than the gym environment of OpenAI (https://gym.openai.com), so that our environment can be integrated with the library (which notably contain some RL algorithms implementation).

The overall basic usage example, given a policy $\Pi$:

In [2]:
from src.env import RunEnv

# Start the game environment with the grid case14, made of 14 substations
env = RunEnv(grid_case=14)
observation = env._get_obs()  # Initial observation

Π = lambda x: None  # Policy

done = True
while not done:
    action = Π(observation)
    observation, reward, done, info = env.step(action)
    
    if info is not None:
        print('Game over!', info)
        pass  # Here you can do things to debug your solution
Using chronics folder /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/chronics/14 and reference grid /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/reference_grid14.m

Context of the experiments

We plan to compare the performance of raw baselines approaches to the problem, that do not take advantage of any training. We define later the explicit behavior of the four baselines to be compared. We design here an experiment that will be conducted by all of the baselines, for fairness in the subsequent comparisons.

Grid used

More explicitaly, the players (or agents) will have to operate a grid known as IEEE-14, also called case14 (officially IEEE-14), which is one of the simplified version of the California power grid. Explicitely, case14 is made of:

  • 14 substations
  • 5 generators
  • 7 consumptions
  • 20 branches

Here is a representation of the overall shape of the case14.

View of IEEE-14

Additional experiment settings:

  • Throughout the game, every line has a thermal limit of 1250 (but this information is not explicitely given to the players or the challengers).
  • The load-flow is on AC mode, such that lines are lossless for instance
  • Cascading failure simulations are limited to a depth of 3
  • By construction, we set the reward related to a load cut (i.e. grid not connexe reward) equal to -5

Apart from the thermal limits and the values of the injections plus the flows, the grid parameters (resistance, reactance etc.) are available at https://github.com/MATPOWER/matpower/blob/master/data/case14.m.

Input chronics

We use predefined values for the injections chronic. Randomly, some productions can be switched-off (output is then 0), which brings some randomness in the data. However, the data was constructed using seasonality, including daily and weekly seasonality (which is usually the case in real-life, e.g. a peak of consumption at 7pm).

Here, we plots the sum of productions per timestep (note that eventually, this code will not be runnable by the challengers):

In [3]:
planned_productions = env.game.chronic.prods_p
print('Number of productions', len(planned_productions[0]))
print('\nNumber of timesteps', len(planned_productions))
print('\nFirst set of productions:', planned_productions[0])

# Plotting the sum of productions for each timestep
sum_productions = np.array([sum(p) for p in planned_productions])
plt.plot(np.arange(1, len(planned_productions)+1), sum_productions, color='c', label='chronics sum of productions')
plt.xlim([0, len(planned_productions)])
# Plot month vertical bars: approx one every 30 days; plot also average productions per month
for i in range(12):
    plt.axvline(x=30*24*i, color='k', linestyle='--', label='month delimiter' if i == 0 else None)  # 30*24 because chronics are hourly updates
    plt.plot(np.arange(30*24*i, 30*24*(i+1)), [sum(sum_productions[30*24*i:30*24*(i+1)+1])/(30.*24.)]*30*24, color='r', label='average per month' if i == 0 else None)
    
plt.ylabel('Sum of hourly productions')
plt.xlabel('Timestep (in hour)')
plt.title('Sum of hourly productions as a function of timestep (1 timestep = 1 hour)')
plt.legend(loc='best')
Number of productions 5

Number of timesteps 8726

First set of productions: [2458.4128  998.1634  751.4649  775.6172  787.9434]
Out[3]:
<matplotlib.legend.Legend at 0x7f63a2259f60>

Zoom on the month of January

In [4]:
length = 28*24
lengthweek = 7*24
lengthday = 24
planned_productions = planned_productions[:length]

# Plotting the sum of productions for each timestep
hourlysum_productions = np.array([sum(p) for p in planned_productions])
plt.plot(np.arange(1, len(planned_productions)+1), hourlysum_productions, color='c', label='chronics sum of productions')
plt.xlim([0, len(planned_productions)])
# Plot week vertical bars: approx one every 30 days; plot also average productions per month
for i in range(4):
    plt.axvline(x=7*24*i, color='m', linestyle='--', label='week delimiter' if i == 0 else None)  # 30*24 because chronics are hourly updates
    
for j in range(4*7):
    plt.plot(np.arange(lengthday*j, lengthday*(j+1)), [sum(hourlysum_productions[lengthday*j:lengthday*(j+1)+1])/(float(lengthday))]*lengthday, color='r', label='average per day' if j == 0 else None)    
    
plt.ylabel('Sum of hourly productions')
plt.xlabel('Timestep (in hour)')
plt.title('Sum of hourly productions as a function of timestep (1 timestep = 1 hour)')
plt.legend(loc='best')
Out[4]:
<matplotlib.legend.Legend at 0x7f63a2149fd0>

Code of the common experiment

All of the baselines will be fed scenarios with the same injections values. Theorically, the grid photos will be different along the baselines since a grid state depends on the actions of a player.

We define here the function that runs a policy Π for our proposed experiment, which lasts for 1000 timesteps:

In [30]:
n_timesteps = 2000
np.random.seed(123)

def run_policy(Π):
    env = RunEnv(grid_case=14)
    observation = env._get_obs()  # Initial observation
    
    # Keep rewards stats
    rewards = []

    current = 0
    while current < n_timesteps:
        action = Π(env, observation)
        observation, reward, done, info = env.step(action)
        
        # Save stats
        rewards.append(reward)
        current += 1
        print('timestep', format(current, '04d'), ' total reward:', np.sum(rewards))
        
        if done:
            observation = env.reset(restart=False)  # Do not restart the game from the initial state
            print('Game over! info:', info)
            continue
    
    return np.asarray(rewards)

Hyperparameters

The reward is based on the sum of 4 subrewards related to:

  • Line capacity usage
  • Load cuts
  • Grid connexity or loadflow error
  • Cost of action
  • Distance to the reference grid
In [31]:
print('line capacity multiplicatif factor:', env.multiplicative_factor_line_usage_reward)
print('grid connexity and loadflow error:', env.connexity_exception_reward, env.loadflow_exception_reward)
print('cost of switch off, cost of node-splitting:', env.cost_line_switch, env.cost_node_switch)
print('cost of switch off, cost of node-splitting:', env.cost_line_switch, env.cost_node_switch)
print('load cut not yet implemented')
line capacity multiplicatif factor: -1.0
grid connexity and loadflow error: -14 -14
cost of switch off, cost of node-splitting: 0 0
cost of switch off, cost of node-splitting: 0 0
load cut not yet implemented

Baselines approaches

We propose four baselines that are all based on hand-crafted policies that do not learn (i.e. no learning parameters). In this section, we define and code each baseline such that they are integrated with our proposed game environment. Specifically, we are intersted in code a policy that takes an observation $o_t$ and returns an action $a_t$: $$ \Pi(a_t|o_t) $$

To do so, all of the baselines have a function baseline_name_policy which takes a state, and output an action. The four baselines are:

  • Do-nothing policy: performs no action whatsoever
  • Random line switch off policy: at each timestep, randomly disconnect one line (and reconnect it back for next timestep)
  • Random node splitting policy: at each timestep, randomly change the topological configuration of one random substation
  • Tree-search line switch-off policy: at each timestep, will simulate the state of the grid with one and only one switched-off line, for all lines

These baselines policies are rudimentary because:

  • they do not learn,
  • the output action do not depend on the current state of the grid $\Pi(a_t|o_t)=\Pi(a_t)$.

Do-nothing policy

The Agent does not perform any action:

$$ \Pi(a_t|o_t) = \varnothing $$

Here is its implementation:

In [32]:
def do_nothing_policy(env, observation_t):
    return None

Random line switch-off policy

The Agent randomly switch-off one line at each timestep. For this task, the topological subaction is None, and the line service status is made of one 0 value, all the others being 1. The 0 value indicate a line to be switched off. Its policy is:

$$ \Pi(a_t|o_t) = [a_t^1, a_t^2]\\ a_t^1=0 \in \{0, 1\}^{n_\mathrm{prods}+n_\mathrm{loads}+2*n_\mathrm{lines}}\\ a_t^2 \in \{0, 1\}^{n_\mathrm{lines}}\mathrm{ s.t. }\exists !i, a_{t, i}^2 = 1\\ $$

In plain words, the action output is a list of two concatenated lists: the first one (concerning nodes on which elements are connected) is 0, the second one is a one-hot vector, where the active component indicates the line status to switch.

The policy can be implemented as:

In [33]:
def random_switch_off_policy(env, observation_t):
    nodes_subaction = np.zeros((env.action_space.n - env.action_space.n_lines,))
    
    status_subaction = np.zeros((env.action_space.n_lines,))
    status_subaction[np.random.randint(len(status_subaction))] = 1
    
    return np.concatenate((nodes_subaction, status_subaction,))

Random node-splitting policy

This Agent is constraint to output node-splitting actions: the subaction of line service status is always None. Specifically, at each timestep, the Agent first chose a random substation. Then, it chose a random configuration for the latter. Its policy can be formulated as:

$$ \Pi(a_t|o_t) = [a_t^1, a_t^2]\\ a_t^1=0 \in \{0, 1\}^{n_\mathrm{prods}+n_\mathrm{loads}+2*n_\mathrm{lines}}\mathrm{ s.t. }\exists !i, a_{t, i}^1 = 1\\ a_t^2 \in \{0, 1\}^{n_\mathrm{lines}}\\ $$$$ \Pi(a_t|o_t) = \{a_t^1, \varnothing\} $$

with $a_t^1=[None, ..., None]$ and $a_t^1[U(1, n_{substations})]=ns$, where $U(a, b)$ is a discrete uniform distribution that returns a random integer between a and b (inclusive here), and $ns$ is a one-hot vector of size the number of possible configurations for the selected substation. Note that some substation only have one bus (or node) where objects can be directly connected (e.g. a substation with at most three elements); the policy do not care about this (and in such a substation, will naturally output a vector [1]).

The policy can be implemented as:

In [34]:
def random_node_splitting_policy(env, observation_t):
    nodes_subaction = np.zeros((env.action_space.n - env.action_space.n_lines,))
    nodes_subaction[np.random.randint(len(nodes_subaction))] = 1
    
    status_subaction = np.zeros((env.action_space.n_lines,))
    
    return np.concatenate((nodes_subaction, status_subaction,))

Tree-search line switch-off policy

At each timestep $t$, the Agent will simulate every possible line switch-off $a_{i, t}^2$, and retrieve the reward $R(s_t, a_{i, t}^2)$. More precisaly, given a grid configuration where all lines are switched-on, the agent will compute $$ r_i = R(s_t, a_{i, t}^2) $$ then $$ a_t = argmax_{a_{i, t}^2} R(s_t, a_{i, t}^2) $$ where $a_{i, t}^2$ is the line switched-off subaction, such that only line $i$ is switched-off. This Agent is apparent to a greedy policy, where the Action Space is constrained to switches-off.

The policy can be implemented as:

In [35]:
def treesearch_switched_off_policy(env, observation_t):
    # Action related to lines service status
    action_size = env.action_space.n
    n_lines = env.action_space.n_lines
    topology_subaction = np.zeros((action_size - n_lines,))
    
    # Retrieves every reward related to every 1-switch-off action
    timestep_rewards = []
    for l in range(n_lines):
        env.game.grid.filename = 'swoff_line%d.m'%l
        print(' Simulation with line %d switched off' % l)
        line_service_subaction = np.zeros((n_lines,))
        line_service_subaction[l] = 1  # Toggle line l
        
        # Construct the action based on two subactions and launch simulation
        action = np.concatenate((topology_subaction, line_service_subaction))
        simulated_reward = env.simulate(action)
        
        timestep_rewards.append(simulated_reward)
    # Compute and append reward of no action
    print(' Simulation with no action')
    env.game.grid.filename = 'nothing.m'
    simulated_reward = env.simulate(None)
    timestep_rewards.append(simulated_reward)
    
    # Get the action that maximizes the reward (construct it based on max of stored rewards)
    argmax_reward = np.argmax(timestep_rewards)
    print('rewards', timestep_rewards, 'argmax', argmax_reward)
    # If last action is best, return no action
    if argmax_reward == len(timestep_rewards)-1:
        print('Action chosen: no action')
        return None
    
    # Else, recompute line status toggle that maximizes reward for this timestep
    line_service_subaction = np.zeros((n_lines,))
    line_service_subaction[argmax_reward] = 1
    action = np.concatenate((topology_subaction, line_service_subaction))
    
    print('Action chosen: switching off line', argmax_reward)
    
    return action

Baselines comparisons

Running the policies

In [36]:
rewards_do_nothing = run_policy(do_nothing_policy)
Using chronics folder /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/chronics/14 and reference grid /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/reference_grid14.m
  Simulating cascading failure
  ok
timestep 0001  total reward: -2.0592410779149573
  Simulating cascading failure
  ok
timestep 0002  total reward: -3.9590646423422813
  Simulating cascading failure
  ok
timestep 0003  total reward: -5.465057867879118
  Simulating cascading failure
  ok
timestep 0004  total reward: -6.985098680162699
  Simulating cascading failure
  ok
timestep 0005  total reward: -8.59357179288142
  Simulating cascading failure
  ok
timestep 0006  total reward: -10.312693429902543
  Simulating cascading failure
  ok
timestep 0007  total reward: -12.337225754464619
  Simulating cascading failure
  ok
timestep 0008  total reward: -14.786425303525743
  Simulating cascading failure
  ok
timestep 0009  total reward: -17.773621161328332
  Simulating cascading failure
  ok
timestep 0010  total reward: -20.988798868940087
  Simulating cascading failure
  ok
timestep 0011  total reward: -24.052592119055088
  Simulating cascading failure
  ok
timestep 0012  total reward: -27.018149245605496
  Simulating cascading failure
  ok
timestep 0013  total reward: -30.08889274770496
  Simulating cascading failure
  ok
timestep 0014  total reward: -33.61251087480954
  Simulating cascading failure
  ok
timestep 0015  total reward: -37.153927390560646
  Simulating cascading failure
  ok
timestep 0016  total reward: -39.90203567261902
  Simulating cascading failure
  ok
timestep 0017  total reward: -42.16103695809912
  Simulating cascading failure
  ok
timestep 0018  total reward: -44.782114717304914
  Simulating cascading failure
  ok
timestep 0019  total reward: -47.63831585374682
  Simulating cascading failure
  ok
timestep 0020  total reward: -50.44858202112856
  Simulating cascading failure
  ok
timestep 0021  total reward: -53.04309590569291
  Simulating cascading failure
  ok
timestep 0022  total reward: -55.99693833014812
  Simulating cascading failure
  ok
timestep 0023  total reward: -59.32502678841367
  Simulating cascading failure
  ok
timestep 0024  total reward: -62.28999980719232
  Simulating cascading failure
  ok
timestep 0025  total reward: -64.51872759485005
  Simulating cascading failure
  ok
timestep 0026  total reward: -66.21850671665737
  Simulating cascading failure
  ok
timestep 0027  total reward: -67.77467092865197
  Simulating cascading failure
  ok
timestep 0028  total reward: -69.18305185492115
  Simulating cascading failure
  ok
timestep 0029  total reward: -70.80144138599746
  Simulating cascading failure
  ok
timestep 0030  total reward: -72.73430759299923
  Simulating cascading failure
  ok
timestep 0031  total reward: -74.97384140429345
  Simulating cascading failure
  ok
timestep 0032  total reward: -77.84879279644238
  Simulating cascading failure
  ok
timestep 0033  total reward: -81.40559706611843
  Simulating cascading failure
  ok
timestep 0034  total reward: -85.31602425127444
  Simulating cascading failure
  ok
timestep 0035  total reward: -89.30144653103514
  Simulating cascading failure
  ok
timestep 0036  total reward: -93.02985865912298
  Simulating cascading failure
  ok
timestep 0037  total reward: -96.81638513920784
  Simulating cascading failure
  ok
timestep 0038  total reward: -100.49561618345842
  Simulating cascading failure
  ok
timestep 0039  total reward: -103.6030498711693
  Simulating cascading failure
  ok
timestep 0040  total reward: -106.49097347167779
  Simulating cascading failure
  ok
timestep 0041  total reward: -109.70810884393306
  Simulating cascading failure
  ok
timestep 0042  total reward: -113.69222801668734
  Simulating cascading failure
  ok
timestep 0043  total reward: -118.43861013811429
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0044  total reward: -132.43861013811429
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0045  total reward: -135.3550094663653
  Simulating cascading failure
  ok
timestep 0046  total reward: -138.3068729253693
  Simulating cascading failure
  ok
timestep 0047  total reward: -141.2098472573536
  Simulating cascading failure
  ok
timestep 0048  total reward: -143.63440125849456
  Simulating cascading failure
  ok
timestep 0049  total reward: -146.05981651767692
  Simulating cascading failure
  ok
timestep 0050  total reward: -148.25848236019107
  Simulating cascading failure
  ok
timestep 0051  total reward: -149.79911956261088
  Simulating cascading failure
  ok
timestep 0052  total reward: -151.28768415816046
  Simulating cascading failure
  ok
timestep 0053  total reward: -153.15020736670766
  Simulating cascading failure
  ok
timestep 0054  total reward: -155.60621461270534
  Simulating cascading failure
  ok
timestep 0055  total reward: -158.3319118981302
  Simulating cascading failure
  ok
timestep 0056  total reward: -161.33184357386307
  Simulating cascading failure
  ok
timestep 0057  total reward: -164.77052087685922
  Simulating cascading failure
  ok
timestep 0058  total reward: -168.54548263042477
  Simulating cascading failure
  ok
timestep 0059  total reward: -172.51771991497884
  Simulating cascading failure
  ok
timestep 0060  total reward: -176.55982222488075
  Simulating cascading failure
  ok
timestep 0061  total reward: -181.18985074591862
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0062  total reward: -195.18985074591862
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0063  total reward: -198.3705968610632
  Simulating cascading failure
  ok
timestep 0064  total reward: -201.44758008555837
  Simulating cascading failure
  ok
timestep 0065  total reward: -204.3180791005683
  Simulating cascading failure
  ok
timestep 0066  total reward: -207.38956145808606
  Simulating cascading failure
  ok
timestep 0067  total reward: -211.00683086006927
  Simulating cascading failure
  ok
timestep 0068  total reward: -214.33754771289045
  Simulating cascading failure
  ok
timestep 0069  total reward: -217.1203825624582
  Simulating cascading failure
  ok
timestep 0070  total reward: -219.99089346636723
  Simulating cascading failure
  ok
timestep 0071  total reward: -223.10030554415349
  Simulating cascading failure
  ok
timestep 0072  total reward: -225.84999825502078
  Simulating cascading failure
  ok
timestep 0073  total reward: -227.9231071154921
  Simulating cascading failure
  ok
timestep 0074  total reward: -229.68224591772102
  Simulating cascading failure
  ok
timestep 0075  total reward: -231.35261487697178
  Simulating cascading failure
  ok
timestep 0076  total reward: -232.84686621814967
  Simulating cascading failure
  ok
timestep 0077  total reward: -234.35643598694023
  Simulating cascading failure
  ok
timestep 0078  total reward: -236.11373586760203
  Simulating cascading failure
  ok
timestep 0079  total reward: -240.10668477512493
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0080  total reward: -254.10668477512496
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0081  total reward: -257.4358751094271
  Simulating cascading failure
  ok
timestep 0082  total reward: -261.23085817272295
  Simulating cascading failure
  ok
timestep 0083  total reward: -265.1357534609102
  Simulating cascading failure
  ok
timestep 0084  total reward: -269.484399886519
  Simulating cascading failure
  ok
timestep 0085  total reward: -273.705857993711
  Simulating cascading failure
  ok
timestep 0086  total reward: -277.0923986016286
  Simulating cascading failure
  ok
timestep 0087  total reward: -280.04981340601825
  Simulating cascading failure
  ok
timestep 0088  total reward: -282.63426397399866
  Simulating cascading failure
  ok
timestep 0089  total reward: -285.16785902778616
  Simulating cascading failure
  ok
timestep 0090  total reward: -288.5264692527152
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0091  total reward: -302.5264692527152
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0092  total reward: -305.9537900790773
  Simulating cascading failure
  ok
timestep 0093  total reward: -308.84752867432445
  Simulating cascading failure
  ok
timestep 0094  total reward: -311.6094733335332
  Simulating cascading failure
  ok
timestep 0095  total reward: -314.5602368077107
  Simulating cascading failure
  ok
timestep 0096  total reward: -317.1570705365157
  Simulating cascading failure
  ok
timestep 0097  total reward: -318.67625794305957
  Simulating cascading failure
  ok
timestep 0098  total reward: -319.74916215910775
  Simulating cascading failure
  ok
timestep 0099  total reward: -321.0146491355524
  Simulating cascading failure
  ok
timestep 0100  total reward: -322.2161164137262
  Simulating cascading failure
  ok
timestep 0101  total reward: -323.68088922616204
  Simulating cascading failure
  ok
timestep 0102  total reward: -325.4157290378069
  Simulating cascading failure
  ok
timestep 0103  total reward: -327.293604815934
  Simulating cascading failure
  ok
timestep 0104  total reward: -329.9024967468233
  Simulating cascading failure
  ok
timestep 0105  total reward: -333.7562638902996
  Simulating cascading failure
  ok
timestep 0106  total reward: -337.37933146185884
  Simulating cascading failure
  ok
timestep 0107  total reward: -340.621035076217
  Simulating cascading failure
  ok
timestep 0108  total reward: -344.2512300015779
  Simulating cascading failure
  ok
timestep 0109  total reward: -347.4762374276075
  Simulating cascading failure
  ok
timestep 0110  total reward: -350.2341003092609
  Simulating cascading failure
  ok
timestep 0111  total reward: -352.967282708382
  Simulating cascading failure
  ok
timestep 0112  total reward: -355.56643224228003
  Simulating cascading failure
  ok
timestep 0113  total reward: -357.9325278928337
  Simulating cascading failure
  ok
timestep 0114  total reward: -360.81404664378863
  Simulating cascading failure
  ok
timestep 0115  total reward: -364.2134049785087
  Simulating cascading failure
  ok
timestep 0116  total reward: -367.2874167762552
  Simulating cascading failure
  ok
timestep 0117  total reward: -369.94916148615425
  Simulating cascading failure
  ok
timestep 0118  total reward: -372.5946586580471
  Simulating cascading failure
  ok
timestep 0119  total reward: -375.25670295083825
  Simulating cascading failure
  ok
timestep 0120  total reward: -377.4462616945293
  Simulating cascading failure
  ok
timestep 0121  total reward: -378.90817535669606
  Simulating cascading failure
  ok
timestep 0122  total reward: -380.1283696185828
  Simulating cascading failure
  ok
timestep 0123  total reward: -381.19814778082355
  Simulating cascading failure
  ok
timestep 0124  total reward: -382.09726695359143
  Simulating cascading failure
  ok
timestep 0125  total reward: -383.0163423631375
  Simulating cascading failure
  ok
timestep 0126  total reward: -384.08991381185206
  Simulating cascading failure
  ok
timestep 0127  total reward: -385.9846048222415
  Simulating cascading failure
  ok
timestep 0128  total reward: -388.345084034042
  Simulating cascading failure
  ok
timestep 0129  total reward: -390.6192780064657
  Simulating cascading failure
  ok
timestep 0130  total reward: -392.9754366426399
  Simulating cascading failure
  ok
timestep 0131  total reward: -395.281118544538
  Simulating cascading failure
  ok
timestep 0132  total reward: -397.70607878598827
  Simulating cascading failure
  ok
timestep 0133  total reward: -400.25080472125217
  Simulating cascading failure
  ok
timestep 0134  total reward: -402.6390510278774
  Simulating cascading failure
  ok
timestep 0135  total reward: -404.54940793756407
  Simulating cascading failure
  ok
timestep 0136  total reward: -406.13817900708193
  Simulating cascading failure
  ok
timestep 0137  total reward: -407.97175760900916
  Simulating cascading failure
  ok
timestep 0138  total reward: -410.42789767884074
  Simulating cascading failure
  ok
timestep 0139  total reward: -413.9815788537696
  Simulating cascading failure
  ok
timestep 0140  total reward: -417.0080794486747
  Simulating cascading failure
  ok
timestep 0141  total reward: -418.66435891264086
  Simulating cascading failure
  ok
timestep 0142  total reward: -420.32717294881695
  Simulating cascading failure
  ok
timestep 0143  total reward: -421.9753551100041
  Simulating cascading failure
  ok
timestep 0144  total reward: -423.28726857700167
  Simulating cascading failure
  ok
timestep 0145  total reward: -424.267785729538
  Simulating cascading failure
  ok
timestep 0146  total reward: -425.0952901043429
  Simulating cascading failure
  ok
timestep 0147  total reward: -425.6603596616555
  Simulating cascading failure
  ok
timestep 0148  total reward: -426.11076130222585
  Simulating cascading failure
  ok
timestep 0149  total reward: -426.82288203214546
  Simulating cascading failure
  ok
timestep 0150  total reward: -427.9644097346684
  Simulating cascading failure
  ok
timestep 0151  total reward: -429.34556836927214
  Simulating cascading failure
  ok
timestep 0152  total reward: -430.80316815658404
  Simulating cascading failure
  ok
timestep 0153  total reward: -432.4947803691319
  Simulating cascading failure
  ok
timestep 0154  total reward: -434.23218189875365
  Simulating cascading failure
  ok
timestep 0155  total reward: -436.0171502772714
  Simulating cascading failure
  ok
timestep 0156  total reward: -437.95947286456544
  Simulating cascading failure
  ok
timestep 0157  total reward: -439.77442857457015
  Simulating cascading failure
  ok
timestep 0158  total reward: -441.7333973976747
  Simulating cascading failure
  ok
timestep 0159  total reward: -443.4893228234779
  Simulating cascading failure
  ok
timestep 0160  total reward: -444.817948472368
  Simulating cascading failure
  ok
timestep 0161  total reward: -446.18472276604655
  Simulating cascading failure
  ok
timestep 0162  total reward: -447.69641960432443
  Simulating cascading failure
  ok
timestep 0163  total reward: -449.38402575488635
  Simulating cascading failure
  ok
timestep 0164  total reward: -450.98790183606695
  Simulating cascading failure
  ok
timestep 0165  total reward: -452.4010555929582
  Simulating cascading failure
  ok
timestep 0166  total reward: -453.7774059086254
  Simulating cascading failure
  ok
timestep 0167  total reward: -455.2215852401308
  Simulating cascading failure
  ok
timestep 0168  total reward: -457.07038746373803
  Simulating cascading failure
  ok
timestep 0169  total reward: -458.89530004392464
  Simulating cascading failure
  ok
timestep 0170  total reward: -460.46960881453276
  Simulating cascading failure
  ok
timestep 0171  total reward: -461.9335884877813
  Simulating cascading failure
  ok
timestep 0172  total reward: -463.1475118612898
  Simulating cascading failure
  ok
timestep 0173  total reward: -464.53643470170164
  Simulating cascading failure
  ok
timestep 0174  total reward: -466.16754517294953
  Simulating cascading failure
  ok
timestep 0175  total reward: -468.2395928050528
  Simulating cascading failure
  ok
timestep 0176  total reward: -470.8383842373718
  Simulating cascading failure
  ok
timestep 0177  total reward: -473.6763555224951
  Simulating cascading failure
  ok
timestep 0178  total reward: -476.7618286094969
  Simulating cascading failure
  ok
timestep 0179  total reward: -480.011586032286
  Simulating cascading failure
  ok
timestep 0180  total reward: -483.32522996128125
  Simulating cascading failure
  ok
timestep 0181  total reward: -486.36085912870936
  Simulating cascading failure
  ok
timestep 0182  total reward: -489.87535298472386
  Simulating cascading failure
  ok
timestep 0183  total reward: -493.42947505890334
  Simulating cascading failure
  ok
timestep 0184  total reward: -495.99996364024537
  Simulating cascading failure
  ok
timestep 0185  total reward: -498.4630589169356
  Simulating cascading failure
  ok
timestep 0186  total reward: -501.645230756216
  Simulating cascading failure
  ok
timestep 0187  total reward: -504.9509058716004
  Simulating cascading failure
  ok
timestep 0188  total reward: -507.9534991706141
  Simulating cascading failure
  ok
timestep 0189  total reward: -511.09102988657355
  Simulating cascading failure
  ok
timestep 0190  total reward: -513.2200950994402
  Simulating cascading failure
  ok
timestep 0191  total reward: -515.0210700014102
  Simulating cascading failure
  ok
timestep 0192  total reward: -517.4842407779365
  Simulating cascading failure
  ok
timestep 0193  total reward: -519.7335118994905
  Simulating cascading failure
  ok
timestep 0194  total reward: -521.8605977385863
  Simulating cascading failure
  ok
timestep 0195  total reward: -523.7084341489151
  Simulating cascading failure
  ok
timestep 0196  total reward: -525.0199649779646
  Simulating cascading failure
  ok
timestep 0197  total reward: -526.3414737325293
  Simulating cascading failure
  ok
timestep 0198  total reward: -528.1504784843142
  Simulating cascading failure
  ok
timestep 0199  total reward: -530.7878587271496
  Simulating cascading failure
  ok
timestep 0200  total reward: -533.9679617208222
  Simulating cascading failure
  ok
timestep 0201  total reward: -537.3519460251711
  Simulating cascading failure
  ok
timestep 0202  total reward: -541.0277586038075
  Simulating cascading failure
  ok
timestep 0203  total reward: -545.342345028697
  Simulating cascading failure
  ok
timestep 0204  total reward: -549.9488503853329
  Simulating cascading failure
  ok
timestep 0205  total reward: -554.6590941129684
  Simulating cascading failure
  ok
timestep 0206  total reward: -558.7423746696104
  Simulating cascading failure
  ok
timestep 0207  total reward: -561.8771999603923
  Simulating cascading failure
  ok
timestep 0208  total reward: -564.8755624590926
  Simulating cascading failure
  ok
timestep 0209  total reward: -567.8155618442578
  Simulating cascading failure
  ok
timestep 0210  total reward: -571.0290520652381
  Simulating cascading failure
  ok
timestep 0211  total reward: -574.5108340146243
  Simulating cascading failure
  ok
timestep 0212  total reward: -577.9292307566077
  Simulating cascading failure
  ok
timestep 0213  total reward: -581.0651271995778
  Simulating cascading failure
  ok
timestep 0214  total reward: -583.9048353097804
  Simulating cascading failure
  ok
timestep 0215  total reward: -587.1449453500502
  Simulating cascading failure
  ok
timestep 0216  total reward: -590.1335346960423
  Simulating cascading failure
  ok
timestep 0217  total reward: -592.1866775905373
  Simulating cascading failure
  ok
timestep 0218  total reward: -593.7384938319749
  Simulating cascading failure
  ok
timestep 0219  total reward: -595.0577719630498
  Simulating cascading failure
  ok
timestep 0220  total reward: -596.7285348612763
  Simulating cascading failure
  ok
timestep 0221  total reward: -598.474808168507
  Simulating cascading failure
  ok
timestep 0222  total reward: -600.2065673613253
  Simulating cascading failure
  ok
timestep 0223  total reward: -602.5448298269541
  Simulating cascading failure
  ok
timestep 0224  total reward: -605.505395892605
  Simulating cascading failure
  ok
timestep 0225  total reward: -607.9876671714966
  Simulating cascading failure
  ok
timestep 0226  total reward: -611.5495875393336
  Simulating cascading failure
  ok
timestep 0227  total reward: -615.8901370010235
  Simulating cascading failure
  ok
timestep 0228  total reward: -619.6017109812892
  Simulating cascading failure
  ok
timestep 0229  total reward: -623.5101264897863
  Simulating cascading failure
  ok
timestep 0230  total reward: -627.0279766237345
  Simulating cascading failure
  ok
timestep 0231  total reward: -630.5981431680021
  Simulating cascading failure
  ok
timestep 0232  total reward: -633.9386466886297
  Simulating cascading failure
  ok
timestep 0233  total reward: -637.6098366982364
  Simulating cascading failure
  ok
timestep 0234  total reward: -641.5243181345569
  Simulating cascading failure
  ok
timestep 0235  total reward: -644.9877605066099
  Simulating cascading failure
  ok
timestep 0236  total reward: -648.5493936736113
  Simulating cascading failure
  ok
timestep 0237  total reward: -651.5914694145794
  Simulating cascading failure
  ok
timestep 0238  total reward: -654.3410474277932
  Simulating cascading failure
  ok
timestep 0239  total reward: -657.1718025892199
  Simulating cascading failure
  ok
timestep 0240  total reward: -659.6185406518275
  Simulating cascading failure
  ok
timestep 0241  total reward: -661.9436949825886
  Simulating cascading failure
  ok
timestep 0242  total reward: -663.9199792913628
  Simulating cascading failure
  ok
timestep 0243  total reward: -665.6613239864956
  Simulating cascading failure
  ok
timestep 0244  total reward: -667.3267017754433
  Simulating cascading failure
  ok
timestep 0245  total reward: -669.0032042407486
  Simulating cascading failure
  ok
timestep 0246  total reward: -671.171108779251
  Simulating cascading failure
  ok
timestep 0247  total reward: -673.7764034300283
  Simulating cascading failure
  ok
timestep 0248  total reward: -676.7202557600405
  Simulating cascading failure
  ok
timestep 0249  total reward: -679.8414409593964
  Simulating cascading failure
  ok
timestep 0250  total reward: -683.3744200258914
  Simulating cascading failure
  ok
timestep 0251  total reward: -687.123755664886
  Simulating cascading failure
  ok
timestep 0252  total reward: -690.7385414105338
  Simulating cascading failure
  ok
timestep 0253  total reward: -694.7624670616881
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0254  total reward: -708.7624670616881
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0255  total reward: -711.8383225584074
  Simulating cascading failure
  ok
timestep 0256  total reward: -714.5569329362575
  Simulating cascading failure
  ok
timestep 0257  total reward: -717.2904056021607
  Simulating cascading failure
  ok
timestep 0258  total reward: -719.6095277536264
  Simulating cascading failure
  ok
timestep 0259  total reward: -721.920305621895
  Simulating cascading failure
  ok
timestep 0260  total reward: -724.9508362478701
  Simulating cascading failure
  ok
timestep 0261  total reward: -727.7822770038911
  Simulating cascading failure
  ok
timestep 0262  total reward: -730.8834617664074
  Simulating cascading failure
  ok
timestep 0263  total reward: -734.4304137842238
  Simulating cascading failure
  ok
timestep 0264  total reward: -737.2241422207663
  Simulating cascading failure
  ok
timestep 0265  total reward: -739.0889633850732
  Simulating cascading failure
  ok
timestep 0266  total reward: -740.8421694029205
  Simulating cascading failure
  ok
timestep 0267  total reward: -742.5833892041012
  Simulating cascading failure
  ok
timestep 0268  total reward: -744.0217372867083
  Simulating cascading failure
  ok
timestep 0269  total reward: -745.4260372733395
  Simulating cascading failure
  ok
timestep 0270  total reward: -747.3137293613555
  Simulating cascading failure
  ok
timestep 0271  total reward: -749.9755624670906
  Simulating cascading failure
  ok
timestep 0272  total reward: -753.1788685642457
  Simulating cascading failure
  ok
timestep 0273  total reward: -756.4790330893852
  Simulating cascading failure
  ok
timestep 0274  total reward: -759.8231055974724
  Simulating cascading failure
  ok
timestep 0275  total reward: -762.971948720986
  Simulating cascading failure
  ok
timestep 0276  total reward: -766.4907978860502
  Simulating cascading failure
  ok
timestep 0277  total reward: -770.159043566083
  Simulating cascading failure
  ok
timestep 0278  total reward: -773.3433664996667
  Simulating cascading failure
  ok
timestep 0279  total reward: -776.3828292061038
  Simulating cascading failure
  ok
timestep 0280  total reward: -779.1926402391657
  Simulating cascading failure
  ok
timestep 0281  total reward: -781.9174918718521
  Simulating cascading failure
  ok
timestep 0282  total reward: -784.9335722833165
  Simulating cascading failure
  ok
timestep 0283  total reward: -788.7251858633142
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0284  total reward: -802.7251858633142
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0285  total reward: -805.7638274300803
  Simulating cascading failure
  ok
timestep 0286  total reward: -808.5457974793902
  Simulating cascading failure
  ok
timestep 0287  total reward: -811.0991451593201
  Simulating cascading failure
  ok
timestep 0288  total reward: -813.0688200419933
  Simulating cascading failure
  ok
timestep 0289  total reward: -814.4175393431636
  Simulating cascading failure
  ok
timestep 0290  total reward: -815.5435097720433
  Simulating cascading failure
  ok
timestep 0291  total reward: -816.5829245137475
  Simulating cascading failure
  ok
timestep 0292  total reward: -817.6692544381874
  Simulating cascading failure
  ok
timestep 0293  total reward: -818.7957054935957
  Simulating cascading failure
  ok
timestep 0294  total reward: -819.6624667326546
  Simulating cascading failure
  ok
timestep 0295  total reward: -820.7278804855548
  Simulating cascading failure
  ok
timestep 0296  total reward: -822.4181183778945
  Simulating cascading failure
  ok
timestep 0297  total reward: -824.4592558894308
  Simulating cascading failure
  ok
timestep 0298  total reward: -826.842102904416
  Simulating cascading failure
  ok
timestep 0299  total reward: -829.2668345230708
  Simulating cascading failure
  ok
timestep 0300  total reward: -831.4330027488629
  Simulating cascading failure
  ok
timestep 0301  total reward: -833.494071690088
  Simulating cascading failure
  ok
timestep 0302  total reward: -835.5880769389854
  Simulating cascading failure
  ok
timestep 0303  total reward: -837.4559983169081
  Simulating cascading failure
  ok
timestep 0304  total reward: -839.2406237831658
  Simulating cascading failure
  ok
timestep 0305  total reward: -841.3833507124928
  Simulating cascading failure
  ok
timestep 0306  total reward: -843.5117822699913
  Simulating cascading failure
  ok
timestep 0307  total reward: -845.5092722059924
  Simulating cascading failure
  ok
timestep 0308  total reward: -847.3650327784324
  Simulating cascading failure
  ok
timestep 0309  total reward: -848.9986993069349
  Simulating cascading failure
  ok
timestep 0310  total reward: -850.6218813000776
  Simulating cascading failure
  ok
timestep 0311  total reward: -852.2122645305781
  Simulating cascading failure
  ok
timestep 0312  total reward: -853.5537181738728
  Simulating cascading failure
  ok
timestep 0313  total reward: -854.274083146398
  Simulating cascading failure
  ok
timestep 0314  total reward: -854.8449997515538
  Simulating cascading failure
  ok
timestep 0315  total reward: -855.6144659407003
  Simulating cascading failure
  ok
timestep 0316  total reward: -856.317155054136
  Simulating cascading failure
  ok
timestep 0317  total reward: -857.291265444419
  Simulating cascading failure
  ok
timestep 0318  total reward: -858.405002680716
  Simulating cascading failure
  ok
timestep 0319  total reward: -859.541303065133
  Simulating cascading failure
  ok
timestep 0320  total reward: -861.1846570198425
  Simulating cascading failure
  ok
timestep 0321  total reward: -862.6340687967057
  Simulating cascading failure
  ok
timestep 0322  total reward: -864.0730557601158
  Simulating cascading failure
  ok
timestep 0323  total reward: -866.0112446781525
  Simulating cascading failure
  ok
timestep 0324  total reward: -867.8956312218479
  Simulating cascading failure
  ok
timestep 0325  total reward: -869.72040308698
  Simulating cascading failure
  ok
timestep 0326  total reward: -871.4506738152744
  Simulating cascading failure
  ok
timestep 0327  total reward: -872.9128489450987
  Simulating cascading failure
  ok
timestep 0328  total reward: -874.1685608377238
  Simulating cascading failure
  ok
timestep 0329  total reward: -875.4424257475147
  Simulating cascading failure
  ok
timestep 0330  total reward: -877.0362365407685
  Simulating cascading failure
  ok
timestep 0331  total reward: -878.7936338465039
  Simulating cascading failure
  ok
timestep 0332  total reward: -880.3805788296002
  Simulating cascading failure
  ok
timestep 0333  total reward: -881.8396726386993
  Simulating cascading failure
  ok
timestep 0334  total reward: -883.1828389951718
  Simulating cascading failure
  ok
timestep 0335  total reward: -884.5011957965518
  Simulating cascading failure
  ok
timestep 0336  total reward: -886.1790061187502
  Simulating cascading failure
  ok
timestep 0337  total reward: -888.1028392067316
  Simulating cascading failure
  ok
timestep 0338  total reward: -890.0313966053302
  Simulating cascading failure
  ok
timestep 0339  total reward: -891.656164339608
  Simulating cascading failure
  ok
timestep 0340  total reward: -892.978641639036
  Simulating cascading failure
  ok
timestep 0341  total reward: -894.4170891697887
  Simulating cascading failure
  ok
timestep 0342  total reward: -896.1863984708862
  Simulating cascading failure
  ok
timestep 0343  total reward: -898.3039804194811
  Simulating cascading failure
  ok
timestep 0344  total reward: -901.2866859782498
  Simulating cascading failure
  ok
timestep 0345  total reward: -904.7164841277422
  Simulating cascading failure
  ok
timestep 0346  total reward: -907.896709894921
  Simulating cascading failure
  ok
timestep 0347  total reward: -911.1692665958126
  Simulating cascading failure
  ok
timestep 0348  total reward: -914.4745140243457
  Simulating cascading failure
  ok
timestep 0349  total reward: -917.6623252703874
  Simulating cascading failure
  ok
timestep 0350  total reward: -920.5241054220049
  Simulating cascading failure
  ok
timestep 0351  total reward: -923.0095050173375
  Simulating cascading failure
  ok
timestep 0352  total reward: -925.2061601213759
  Simulating cascading failure
  ok
timestep 0353  total reward: -927.5670430620305
  Simulating cascading failure
  ok
timestep 0354  total reward: -931.1198932386553
  Simulating cascading failure
  ok
timestep 0355  total reward: -935.1997026912395
  Simulating cascading failure
  ok
timestep 0356  total reward: -938.1486354309634
  Simulating cascading failure
  ok
timestep 0357  total reward: -940.2833972961771
  Simulating cascading failure
  ok
timestep 0358  total reward: -942.3365809185493
  Simulating cascading failure
  ok
timestep 0359  total reward: -944.618635202956
  Simulating cascading failure
  ok
timestep 0360  total reward: -947.5671391518651
  Simulating cascading failure
  ok
timestep 0361  total reward: -950.6953870401901
  Simulating cascading failure
  ok
timestep 0362  total reward: -953.4620013566357
  Simulating cascading failure
  ok
timestep 0363  total reward: -955.8227602848665
  Simulating cascading failure
  ok
timestep 0364  total reward: -957.8267288290242
  Simulating cascading failure
  ok
timestep 0365  total reward: -960.1880224304923
  Simulating cascading failure
  ok
timestep 0366  total reward: -963.1662884375489
  Simulating cascading failure
  ok
timestep 0367  total reward: -966.6660856073411
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0368  total reward: -980.6660856073412
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0369  total reward: -994.6660856073412
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0370  total reward: -1008.6660856073412
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0371  total reward: -1022.6660856073413
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0372  total reward: -1036.6660856073413
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0373  total reward: -1050.6660856073413
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0374  total reward: -1064.6660856073413
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0375  total reward: -1068.7054763727274
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0376  total reward: -1082.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0377  total reward: -1096.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0378  total reward: -1110.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0379  total reward: -1124.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0380  total reward: -1138.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0381  total reward: -1152.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0382  total reward: -1166.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0383  total reward: -1180.7054763727274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0384  total reward: -1194.7054763727272
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0385  total reward: -1196.6677973603096
  Simulating cascading failure
  ok
timestep 0386  total reward: -1198.9323194187111
  Simulating cascading failure
  ok
timestep 0387  total reward: -1200.8302193324782
  Simulating cascading failure
  ok
timestep 0388  total reward: -1201.8261498727825
  Simulating cascading failure
  ok
timestep 0389  total reward: -1202.8891286677617
  Simulating cascading failure
  ok
timestep 0390  total reward: -1204.6403508088656
  Simulating cascading failure
  ok
timestep 0391  total reward: -1207.0716133181013
  Simulating cascading failure
  ok
timestep 0392  total reward: -1210.1350776976042
  Simulating cascading failure
  ok
timestep 0393  total reward: -1214.3106731283406
  Simulating cascading failure
  ok
timestep 0394  total reward: -1218.588917113869
  Simulating cascading failure
  ok
timestep 0395  total reward: -1222.377010604775
  Simulating cascading failure
  ok
timestep 0396  total reward: -1226.1509665568308
  Simulating cascading failure
  ok
timestep 0397  total reward: -1229.6945801434917
  Simulating cascading failure
  ok
timestep 0398  total reward: -1232.9815754339475
  Simulating cascading failure
  ok
timestep 0399  total reward: -1235.6768212618333
  Simulating cascading failure
  ok
timestep 0400  total reward: -1238.173660122577
  Simulating cascading failure
  ok
timestep 0401  total reward: -1240.3339883816418
  Simulating cascading failure
  ok
timestep 0402  total reward: -1242.814782121271
  Simulating cascading failure
  ok
timestep 0403  total reward: -1246.2444383396419
  Simulating cascading failure
  ok
timestep 0404  total reward: -1249.6284734915466
  Simulating cascading failure
  ok
timestep 0405  total reward: -1252.4562603645836
  Simulating cascading failure
  ok
timestep 0406  total reward: -1256.605721259596
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0407  total reward: -1270.605721259596
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0408  total reward: -1272.6092102085827
  Simulating cascading failure
  ok
timestep 0409  total reward: -1274.587038447578
  Simulating cascading failure
  ok
timestep 0410  total reward: -1276.1817356681927
  Simulating cascading failure
  ok
timestep 0411  total reward: -1277.7337027835335
  Simulating cascading failure
  ok
timestep 0412  total reward: -1279.2169584132369
  Simulating cascading failure
  ok
timestep 0413  total reward: -1280.785659498065
  Simulating cascading failure
  ok
timestep 0414  total reward: -1282.6107954270478
  Simulating cascading failure
  ok
timestep 0415  total reward: -1284.2909292321945
  Simulating cascading failure
  ok
timestep 0416  total reward: -1287.2075790789927
  Simulating cascading failure
  ok
timestep 0417  total reward: -1291.3321537600007
  Simulating cascading failure
  ok
timestep 0418  total reward: -1295.7703361166582
  Simulating cascading failure
  ok
timestep 0419  total reward: -1300.2546354038432
  Simulating cascading failure
  ok
timestep 0420  total reward: -1304.2783136474561
  Simulating cascading failure
  ok
timestep 0421  total reward: -1308.6720350746286
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0422  total reward: -1322.6720350746286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0423  total reward: -1326.7289743971303
  Simulating cascading failure
  ok
timestep 0424  total reward: -1330.5343989836692
  Simulating cascading failure
  ok
timestep 0425  total reward: -1333.2792457088713
  Simulating cascading failure
  ok
timestep 0426  total reward: -1336.3491952129789
  Simulating cascading failure
  ok
timestep 0427  total reward: -1339.8276732866539
  Simulating cascading failure
  ok
timestep 0428  total reward: -1343.2784192761897
  Simulating cascading failure
  ok
timestep 0429  total reward: -1346.643037287262
  Simulating cascading failure
  ok
timestep 0430  total reward: -1350.0308087869792
  Simulating cascading failure
  ok
timestep 0431  total reward: -1353.88164833659
  Simulating cascading failure
  ok
timestep 0432  total reward: -1357.4308253503439
  Simulating cascading failure
  ok
timestep 0433  total reward: -1359.6158997243556
  Simulating cascading failure
  ok
timestep 0434  total reward: -1361.4617755480476
  Simulating cascading failure
  ok
timestep 0435  total reward: -1363.2934526566594
  Simulating cascading failure
  ok
timestep 0436  total reward: -1364.7650652096418
  Simulating cascading failure
  ok
timestep 0437  total reward: -1366.147602262097
  Simulating cascading failure
  ok
timestep 0438  total reward: -1367.972349390994
  Simulating cascading failure
  ok
timestep 0439  total reward: -1370.3202339425927
  Simulating cascading failure
  ok
timestep 0440  total reward: -1373.6175659944638
  Simulating cascading failure
  ok
timestep 0441  total reward: -1377.4944112436463
  Simulating cascading failure
  ok
timestep 0442  total reward: -1380.9031856715465
  Simulating cascading failure
  ok
timestep 0443  total reward: -1384.3586622578846
  Simulating cascading failure
  ok
timestep 0444  total reward: -1388.1513106020604
  Simulating cascading failure
  ok
timestep 0445  total reward: -1391.706238329681
  Simulating cascading failure
  ok
timestep 0446  total reward: -1394.8813828999316
  Simulating cascading failure
  ok
timestep 0447  total reward: -1397.7821571583904
  Simulating cascading failure
  ok
timestep 0448  total reward: -1400.378569547425
  Simulating cascading failure
  ok
timestep 0449  total reward: -1402.9645175248813
  Simulating cascading failure
  ok
timestep 0450  total reward: -1405.8290195874354
  Simulating cascading failure
  ok
timestep 0451  total reward: -1409.0614443483162
  Simulating cascading failure
  ok
timestep 0452  total reward: -1412.1933042475694
  Simulating cascading failure
  ok
timestep 0453  total reward: -1414.8522397340344
  Simulating cascading failure
  ok
timestep 0454  total reward: -1417.365792618145
  Simulating cascading failure
  ok
timestep 0455  total reward: -1420.2817980395744
  Simulating cascading failure
  ok
timestep 0456  total reward: -1422.6565607774191
  Simulating cascading failure
  ok
timestep 0457  total reward: -1423.7115541899666
  Simulating cascading failure
  ok
timestep 0458  total reward: -1424.3216452043107
  Simulating cascading failure
  ok
timestep 0459  total reward: -1425.0275647624221
  Simulating cascading failure
  ok
timestep 0460  total reward: -1425.895305175009
  Simulating cascading failure
  ok
timestep 0461  total reward: -1426.899228896061
  Simulating cascading failure
  ok
timestep 0462  total reward: -1428.1772234717828
  Simulating cascading failure
  ok
timestep 0463  total reward: -1429.6658205580038
  Simulating cascading failure
  ok
timestep 0464  total reward: -1431.4515283884666
  Simulating cascading failure
  ok
timestep 0465  total reward: -1433.5861421496534
  Simulating cascading failure
  ok
timestep 0466  total reward: -1435.8002809663872
  Simulating cascading failure
  ok
timestep 0467  total reward: -1438.556017030344
  Simulating cascading failure
  ok
timestep 0468  total reward: -1441.4563779275286
  Simulating cascading failure
  ok
timestep 0469  total reward: -1444.0730459533438
  Simulating cascading failure
  ok
timestep 0470  total reward: -1446.5180688442288
  Simulating cascading failure
  ok
timestep 0471  total reward: -1448.4944489277082
  Simulating cascading failure
  ok
timestep 0472  total reward: -1450.2395551191248
  Simulating cascading failure
  ok
timestep 0473  total reward: -1451.880505488502
  Simulating cascading failure
  ok
timestep 0474  total reward: -1453.5647420979424
  Simulating cascading failure
  ok
timestep 0475  total reward: -1456.0064486140968
  Simulating cascading failure
  ok
timestep 0476  total reward: -1458.6052739864112
  Simulating cascading failure
  ok
timestep 0477  total reward: -1460.4341473245897
  Simulating cascading failure
  ok
timestep 0478  total reward: -1462.0473211923795
  Simulating cascading failure
  ok
timestep 0479  total reward: -1463.7142132026904
  Simulating cascading failure
  ok
timestep 0480  total reward: -1465.2901990592386
  Simulating cascading failure
  ok
timestep 0481  total reward: -1466.5172743042492
  Simulating cascading failure
  ok
timestep 0482  total reward: -1467.4399917439405
  Simulating cascading failure
  ok
timestep 0483  total reward: -1468.1947808195646
  Simulating cascading failure
  ok
timestep 0484  total reward: -1468.8859475598292
  Simulating cascading failure
  ok
timestep 0485  total reward: -1469.7655873728634
  Simulating cascading failure
  ok
timestep 0486  total reward: -1470.7598800086803
  Simulating cascading failure
  ok
timestep 0487  total reward: -1471.934987071212
  Simulating cascading failure
  ok
timestep 0488  total reward: -1473.4218302381205
  Simulating cascading failure
  ok
timestep 0489  total reward: -1475.0383926172256
  Simulating cascading failure
  ok
timestep 0490  total reward: -1477.09022064665
  Simulating cascading failure
  ok
timestep 0491  total reward: -1479.1192601537723
  Simulating cascading failure
  ok
timestep 0492  total reward: -1480.900775978222
  Simulating cascading failure
  ok
timestep 0493  total reward: -1482.6674052695091
  Simulating cascading failure
  ok
timestep 0494  total reward: -1484.2754555013837
  Simulating cascading failure
  ok
timestep 0495  total reward: -1485.7864058377704
  Simulating cascading failure
  ok
timestep 0496  total reward: -1487.2108780155108
  Simulating cascading failure
  ok
timestep 0497  total reward: -1488.7443418164999
  Simulating cascading failure
  ok
timestep 0498  total reward: -1490.351673864302
  Simulating cascading failure
  ok
timestep 0499  total reward: -1492.0202886874831
  Simulating cascading failure
  ok
timestep 0500  total reward: -1493.6445906261551
  Simulating cascading failure
  ok
timestep 0501  total reward: -1495.1958991285474
  Simulating cascading failure
  ok
timestep 0502  total reward: -1496.8033485742646
  Simulating cascading failure
  ok
timestep 0503  total reward: -1498.5143600553142
  Simulating cascading failure
  ok
timestep 0504  total reward: -1500.7366182333817
  Simulating cascading failure
  ok
timestep 0505  total reward: -1502.8527069097668
  Simulating cascading failure
  ok
timestep 0506  total reward: -1504.3529533294186
  Simulating cascading failure
  ok
timestep 0507  total reward: -1505.6576800660382
  Simulating cascading failure
  ok
timestep 0508  total reward: -1506.8410491920017
  Simulating cascading failure
  ok
timestep 0509  total reward: -1508.3295544762423
  Simulating cascading failure
  ok
timestep 0510  total reward: -1510.0499230091068
  Simulating cascading failure
  ok
timestep 0511  total reward: -1511.9765648303237
  Simulating cascading failure
  ok
timestep 0512  total reward: -1514.5987753893457
  Simulating cascading failure
  ok
timestep 0513  total reward: -1516.8235482488249
  Simulating cascading failure
  ok
timestep 0514  total reward: -1518.3555666739223
  Simulating cascading failure
  ok
timestep 0515  total reward: -1520.9409496683413
  Simulating cascading failure
  ok
timestep 0516  total reward: -1524.2974560719265
  Simulating cascading failure
  ok
timestep 0517  total reward: -1527.804080927544
  Simulating cascading failure
  ok
timestep 0518  total reward: -1530.8706273312648
  Simulating cascading failure
  ok
timestep 0519  total reward: -1533.2226671848694
  Simulating cascading failure
  ok
timestep 0520  total reward: -1535.5523060572486
  Simulating cascading failure
  ok
timestep 0521  total reward: -1537.9777990102712
  Simulating cascading failure
  ok
timestep 0522  total reward: -1540.6469098594364
  Simulating cascading failure
  ok
timestep 0523  total reward: -1543.5590199328324
  Simulating cascading failure
  ok
timestep 0524  total reward: -1546.4640914046574
  Simulating cascading failure
  ok
timestep 0525  total reward: -1548.934578763801
  Simulating cascading failure
  ok
timestep 0526  total reward: -1551.3098411577719
  Simulating cascading failure
  ok
timestep 0527  total reward: -1553.9239886020584
  Simulating cascading failure
  ok
timestep 0528  total reward: -1556.4624246336696
  Simulating cascading failure
  ok
timestep 0529  total reward: -1558.626230973282
  Simulating cascading failure
  ok
timestep 0530  total reward: -1560.6090614457416
  Simulating cascading failure
  ok
timestep 0531  total reward: -1562.2581331170554
  Simulating cascading failure
  ok
timestep 0532  total reward: -1563.8417278900974
  Simulating cascading failure
  ok
timestep 0533  total reward: -1565.516871659479
  Simulating cascading failure
  ok
timestep 0534  total reward: -1567.3469068685763
  Simulating cascading failure
  ok
timestep 0535  total reward: -1569.8104263995974
  Simulating cascading failure
  ok
timestep 0536  total reward: -1572.841780313011
  Simulating cascading failure
  ok
timestep 0537  total reward: -1575.3233106796838
  Simulating cascading failure
  ok
timestep 0538  total reward: -1577.8968618882927
  Simulating cascading failure
  ok
timestep 0539  total reward: -1581.485875256894
  Simulating cascading failure
  ok
timestep 0540  total reward: -1585.4046618277973
  Simulating cascading failure
  ok
timestep 0541  total reward: -1589.0489222270091
  Simulating cascading failure
  ok
timestep 0542  total reward: -1592.1574530158273
  Simulating cascading failure
  ok
timestep 0543  total reward: -1595.4853726005886
  Simulating cascading failure
  ok
timestep 0544  total reward: -1598.5078286181108
  Simulating cascading failure
  ok
timestep 0545  total reward: -1601.112909519499
  Simulating cascading failure
  ok
timestep 0546  total reward: -1604.3032052496046
  Simulating cascading failure
  ok
timestep 0547  total reward: -1608.6637489127943
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0548  total reward: -1622.6637489127943
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0549  total reward: -1625.3247789474317
  Simulating cascading failure
  ok
timestep 0550  total reward: -1627.8031646271397
  Simulating cascading failure
  ok
timestep 0551  total reward: -1629.6398101824607
  Simulating cascading failure
  ok
timestep 0552  total reward: -1631.3068928627904
  Simulating cascading failure
  ok
timestep 0553  total reward: -1633.7787902960415
  Simulating cascading failure
  ok
timestep 0554  total reward: -1636.0763074674633
  Simulating cascading failure
  ok
timestep 0555  total reward: -1637.7195285864384
  Simulating cascading failure
  ok
timestep 0556  total reward: -1639.1824796519404
  Simulating cascading failure
  ok
timestep 0557  total reward: -1640.6377710581337
  Simulating cascading failure
  ok
timestep 0558  total reward: -1642.5079751592295
  Simulating cascading failure
  ok
timestep 0559  total reward: -1644.816837030889
  Simulating cascading failure
  ok
timestep 0560  total reward: -1647.6237878106094
  Simulating cascading failure
  ok
timestep 0561  total reward: -1651.0897354053182
  Simulating cascading failure
  ok
timestep 0562  total reward: -1654.7738208538165
  Simulating cascading failure
  ok
timestep 0563  total reward: -1658.4962354503919
  Simulating cascading failure
  ok
timestep 0564  total reward: -1662.2115963183978
  Simulating cascading failure
  ok
timestep 0565  total reward: -1665.8226259892187
  Simulating cascading failure
  ok
timestep 0566  total reward: -1668.4846456314572
  Simulating cascading failure
  ok
timestep 0567  total reward: -1670.894614681083
  Simulating cascading failure
  ok
timestep 0568  total reward: -1673.9344472057037
  Simulating cascading failure
  ok
timestep 0569  total reward: -1676.816617243576
  Simulating cascading failure
  ok
timestep 0570  total reward: -1680.4873140755185
  Simulating cascading failure
  ok
timestep 0571  total reward: -1684.6265807218588
  Simulating cascading failure
  ok
timestep 0572  total reward: -1687.889176535151
  Simulating cascading failure
  ok
timestep 0573  total reward: -1691.2671715036336
  Simulating cascading failure
  ok
timestep 0574  total reward: -1694.613279898968
  Simulating cascading failure
  ok
timestep 0575  total reward: -1697.4925603525485
  Simulating cascading failure
  ok
timestep 0576  total reward: -1700.0041930898085
  Simulating cascading failure
  ok
timestep 0577  total reward: -1702.2915775187707
  Simulating cascading failure
  ok
timestep 0578  total reward: -1704.4284805960783
  Simulating cascading failure
  ok
timestep 0579  total reward: -1705.6014963010489
  Simulating cascading failure
  ok
timestep 0580  total reward: -1706.6386750827628
  Simulating cascading failure
  ok
timestep 0581  total reward: -1707.7817833333615
  Simulating cascading failure
  ok
timestep 0582  total reward: -1709.2346494789313
  Simulating cascading failure
  ok
timestep 0583  total reward: -1711.5852333304176
  Simulating cascading failure
  ok
timestep 0584  total reward: -1714.4348653012157
  Simulating cascading failure
  ok
timestep 0585  total reward: -1717.5506465369037
  Simulating cascading failure
  ok
timestep 0586  total reward: -1720.720703302718
  Simulating cascading failure
  ok
timestep 0587  total reward: -1724.2632093886677
  Simulating cascading failure
  ok
timestep 0588  total reward: -1728.0481648664963
  Simulating cascading failure
  ok
timestep 0589  total reward: -1731.6578575357594
  Simulating cascading failure
  ok
timestep 0590  total reward: -1734.9973212757927
  Simulating cascading failure
  ok
timestep 0591  total reward: -1738.0050314898554
  Simulating cascading failure
  ok
timestep 0592  total reward: -1740.7646740964824
  Simulating cascading failure
  ok
timestep 0593  total reward: -1743.6915075600996
  Simulating cascading failure
  ok
timestep 0594  total reward: -1747.1329788899407
  Simulating cascading failure
  ok
timestep 0595  total reward: -1750.7742527594328
  Simulating cascading failure
  ok
timestep 0596  total reward: -1754.1389363440942
  Simulating cascading failure
  ok
timestep 0597  total reward: -1756.926969926751
  Simulating cascading failure
  ok
timestep 0598  total reward: -1759.6254731335362
  Simulating cascading failure
  ok
timestep 0599  total reward: -1763.2863301839197
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0600  total reward: -1777.2863301839197
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0601  total reward: -1779.9742801778743
  Simulating cascading failure
  ok
timestep 0602  total reward: -1782.657926619765
  Simulating cascading failure
  ok
timestep 0603  total reward: -1784.4058039333013
  Simulating cascading failure
  ok
timestep 0604  total reward: -1786.0104747567548
  Simulating cascading failure
  ok
timestep 0605  total reward: -1787.5421357923447
  Simulating cascading failure
  ok
timestep 0606  total reward: -1789.277302178943
  Simulating cascading failure
  ok
timestep 0607  total reward: -1791.3380091151307
  Simulating cascading failure
  ok
timestep 0608  total reward: -1794.21763110698
  Simulating cascading failure
  ok
timestep 0609  total reward: -1797.6717128678729
  Simulating cascading failure
  ok
timestep 0610  total reward: -1801.0580033240533
  Simulating cascading failure
  ok
timestep 0611  total reward: -1804.6073457553184
  Simulating cascading failure
  ok
timestep 0612  total reward: -1808.1726776029889
  Simulating cascading failure
  ok
timestep 0613  total reward: -1812.1367025126399
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0614  total reward: -1826.1367025126399
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0615  total reward: -1829.3657485241743
  Simulating cascading failure
  ok
timestep 0616  total reward: -1832.81137782522
  Simulating cascading failure
  ok
timestep 0617  total reward: -1835.7856528003347
  Simulating cascading failure
  ok
timestep 0618  total reward: -1837.9999483516558
  Simulating cascading failure
  ok
timestep 0619  total reward: -1840.4728330926073
  Simulating cascading failure
  ok
timestep 0620  total reward: -1843.3178115511553
  Simulating cascading failure
  ok
timestep 0621  total reward: -1845.863578385321
  Simulating cascading failure
  ok
timestep 0622  total reward: -1848.4870206012383
  Simulating cascading failure
  ok
timestep 0623  total reward: -1851.0258585042425
  Simulating cascading failure
  ok
timestep 0624  total reward: -1853.0200704934616
  Simulating cascading failure
  ok
timestep 0625  total reward: -1854.403449450512
  Simulating cascading failure
  ok
timestep 0626  total reward: -1855.6836950027055
  Simulating cascading failure
  ok
timestep 0627  total reward: -1856.8294130302302
  Simulating cascading failure
  ok
timestep 0628  total reward: -1857.7335012165836
  Simulating cascading failure
  ok
timestep 0629  total reward: -1858.680717843118
  Simulating cascading failure
  ok
timestep 0630  total reward: -1859.776313419311
  Simulating cascading failure
  ok
timestep 0631  total reward: -1861.163918640936
  Simulating cascading failure
  ok
timestep 0632  total reward: -1863.0633040151374
  Simulating cascading failure
  ok
timestep 0633  total reward: -1865.164885949072
  Simulating cascading failure
  ok
timestep 0634  total reward: -1867.2993627853955
  Simulating cascading failure
  ok
timestep 0635  total reward: -1869.5157131401952
  Simulating cascading failure
  ok
timestep 0636  total reward: -1872.2334380587274
  Simulating cascading failure
  ok
timestep 0637  total reward: -1874.9588314717107
  Simulating cascading failure
  ok
timestep 0638  total reward: -1877.1346219316558
  Simulating cascading failure
  ok
timestep 0639  total reward: -1879.173155901645
  Simulating cascading failure
  ok
timestep 0640  total reward: -1880.907583994541
  Simulating cascading failure
  ok
timestep 0641  total reward: -1882.580890394408
  Simulating cascading failure
  ok
timestep 0642  total reward: -1884.8756425060328
  Simulating cascading failure
  ok
timestep 0643  total reward: -1887.1676479455225
  Simulating cascading failure
  ok
timestep 0644  total reward: -1889.2016461049643
  Simulating cascading failure
  ok
timestep 0645  total reward: -1890.8767400022455
  Simulating cascading failure
  ok
timestep 0646  total reward: -1892.3580891314875
  Simulating cascading failure
  ok
timestep 0647  total reward: -1894.1692545960605
  Simulating cascading failure
  ok
timestep 0648  total reward: -1895.8270525890337
  Simulating cascading failure
  ok
timestep 0649  total reward: -1897.106482578111
  Simulating cascading failure
  ok
timestep 0650  total reward: -1898.0249500364894
  Simulating cascading failure
  ok
timestep 0651  total reward: -1898.8966444772348
  Simulating cascading failure
  ok
timestep 0652  total reward: -1899.6751320425221
  Simulating cascading failure
  ok
timestep 0653  total reward: -1900.3916190571267
  Simulating cascading failure
  ok
timestep 0654  total reward: -1901.2429792028572
  Simulating cascading failure
  ok
timestep 0655  total reward: -1902.3385239430534
  Simulating cascading failure
  ok
timestep 0656  total reward: -1903.7675631534366
  Simulating cascading failure
  ok
timestep 0657  total reward: -1905.4247438640612
  Simulating cascading failure
  ok
timestep 0658  total reward: -1907.1333071088839
  Simulating cascading failure
  ok
timestep 0659  total reward: -1909.3018571347404
  Simulating cascading failure
  ok
timestep 0660  total reward: -1911.7071503673565
  Simulating cascading failure
  ok
timestep 0661  total reward: -1913.6925323762243
  Simulating cascading failure
  ok
timestep 0662  total reward: -1915.5865445857296
  Simulating cascading failure
  ok
timestep 0663  total reward: -1917.287263513403
  Simulating cascading failure
  ok
timestep 0664  total reward: -1918.6581755532175
  Simulating cascading failure
  ok
timestep 0665  total reward: -1920.0882807791672
  Simulating cascading failure
  ok
timestep 0666  total reward: -1921.9798205482443
  Simulating cascading failure
  ok
timestep 0667  total reward: -1924.0811893070857
  Simulating cascading failure
  ok
timestep 0668  total reward: -1925.7683902479635
  Simulating cascading failure
  ok
timestep 0669  total reward: -1927.2114194766111
  Simulating cascading failure
  ok
timestep 0670  total reward: -1928.5832190386332
  Simulating cascading failure
  ok
timestep 0671  total reward: -1929.8817047047758
  Simulating cascading failure
  ok
timestep 0672  total reward: -1931.4831990132616
  Simulating cascading failure
  ok
timestep 0673  total reward: -1933.4749912269394
  Simulating cascading failure
  ok
timestep 0674  total reward: -1935.1935094898877
  Simulating cascading failure
  ok
timestep 0675  total reward: -1936.482165962696
  Simulating cascading failure
  ok
timestep 0676  total reward: -1937.695455149846
  Simulating cascading failure
  ok
timestep 0677  total reward: -1939.1496509556118
  Simulating cascading failure
  ok
timestep 0678  total reward: -1940.4758540181065
  Simulating cascading failure
  ok
timestep 0679  total reward: -1942.2740465636657
  Simulating cascading failure
  ok
timestep 0680  total reward: -1944.8940018875383
  Simulating cascading failure
  ok
timestep 0681  total reward: -1947.767827392805
  Simulating cascading failure
  ok
timestep 0682  total reward: -1950.9092100144203
  Simulating cascading failure
  ok
timestep 0683  total reward: -1954.1922639651157
  Simulating cascading failure
  ok
timestep 0684  total reward: -1956.7330181452053
  Simulating cascading failure
  ok
timestep 0685  total reward: -1959.1927870274021
  Simulating cascading failure
  ok
timestep 0686  total reward: -1962.3410661840448
  Simulating cascading failure
  ok
timestep 0687  total reward: -1965.1311624655027
  Simulating cascading failure
  ok
timestep 0688  total reward: -1967.4426485866634
  Simulating cascading failure
  ok
timestep 0689  total reward: -1969.0330933208243
  Simulating cascading failure
  ok
timestep 0690  total reward: -1970.9889322467259
  Simulating cascading failure
  ok
timestep 0691  total reward: -1973.6671878986326
  Simulating cascading failure
  ok
timestep 0692  total reward: -1976.7001491444666
  Simulating cascading failure
  ok
timestep 0693  total reward: -1979.5820965266644
  Simulating cascading failure
  ok
timestep 0694  total reward: -1982.1305017921554
  Simulating cascading failure
  ok
timestep 0695  total reward: -1984.7086331102535
  Simulating cascading failure
  ok
timestep 0696  total reward: -1987.1610326851333
  Simulating cascading failure
  ok
timestep 0697  total reward: -1989.4087539774016
  Simulating cascading failure
  ok
timestep 0698  total reward: -1991.1690710538992
  Simulating cascading failure
  ok
timestep 0699  total reward: -1992.814292634935
  Simulating cascading failure
  ok
timestep 0700  total reward: -1994.3514315333873
  Simulating cascading failure
  ok
timestep 0701  total reward: -1995.7469050306995
  Simulating cascading failure
  ok
timestep 0702  total reward: -1997.4592121531873
  Simulating cascading failure
  ok
timestep 0703  total reward: -1999.653796142302
  Simulating cascading failure
  ok
timestep 0704  total reward: -2002.5220127968914
  Simulating cascading failure
  ok
timestep 0705  total reward: -2005.9973545514545
  Simulating cascading failure
  ok
timestep 0706  total reward: -2009.5887696038228
  Simulating cascading failure
  ok
timestep 0707  total reward: -2013.7754792905694
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0708  total reward: -2027.7754792905694
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0709  total reward: -2041.7754792905694
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0710  total reward: -2045.1518856065782
  Simulating cascading failure
  ok
timestep 0711  total reward: -2047.99329632793
  Simulating cascading failure
  ok
timestep 0712  total reward: -2051.113396633144
  Simulating cascading failure
  ok
timestep 0713  total reward: -2054.3408161003345
  Simulating cascading failure
  ok
timestep 0714  total reward: -2058.560371467246
  Simulating cascading failure
  ok
timestep 0715  total reward: -2063.6948290360933
  Simulating cascading failure
  ok
timestep 0716  total reward: -2067.5884149004914
  Simulating cascading failure
  ok
timestep 0717  total reward: -2070.5362767639763
  Simulating cascading failure
  ok
timestep 0718  total reward: -2073.3238477345653
  Simulating cascading failure
  ok
timestep 0719  total reward: -2076.051017667843
  Simulating cascading failure
  ok
timestep 0720  total reward: -2078.439102857531
  Simulating cascading failure
  ok
timestep 0721  total reward: -2080.670449670287
  Simulating cascading failure
  ok
timestep 0722  total reward: -2082.645057071585
  Simulating cascading failure
  ok
timestep 0723  total reward: -2084.1284152973344
  Simulating cascading failure
  ok
timestep 0724  total reward: -2085.520041120916
  Simulating cascading failure
  ok
timestep 0725  total reward: -2087.122726790434
  Simulating cascading failure
  ok
timestep 0726  total reward: -2088.9875843309746
  Simulating cascading failure
  ok
timestep 0727  total reward: -2091.4846010272936
  Simulating cascading failure
  ok
timestep 0728  total reward: -2094.904331943758
  Simulating cascading failure
  ok
timestep 0729  total reward: -2098.4731056756737
  Simulating cascading failure
  ok
timestep 0730  total reward: -2101.755805603236
  Simulating cascading failure
  ok
timestep 0731  total reward: -2105.220235738192
  Simulating cascading failure
  ok
timestep 0732  total reward: -2109.187962397492
  Simulating cascading failure
  ok
timestep 0733  total reward: -2112.9544414423563
  Simulating cascading failure
  ok
timestep 0734  total reward: -2116.040716600347
  Simulating cascading failure
  ok
timestep 0735  total reward: -2118.7885765307055
  Simulating cascading failure
  ok
timestep 0736  total reward: -2121.5013468220795
  Simulating cascading failure
  ok
timestep 0737  total reward: -2124.48609843047
  Simulating cascading failure
  ok
timestep 0738  total reward: -2127.585863536416
  Simulating cascading failure
  ok
timestep 0739  total reward: -2131.0380037777763
  Simulating cascading failure
  ok
timestep 0740  total reward: -2135.0090382334333
  Simulating cascading failure
  ok
timestep 0741  total reward: -2138.27806066151
  Simulating cascading failure
  ok
timestep 0742  total reward: -2141.3615556060167
  Simulating cascading failure
  ok
timestep 0743  total reward: -2144.5782452716885
  Simulating cascading failure
  ok
timestep 0744  total reward: -2147.8602284026633
  Simulating cascading failure
  ok
timestep 0745  total reward: -2151.479872567994
  Simulating cascading failure
  ok
timestep 0746  total reward: -2154.599255169464
  Simulating cascading failure
  ok
timestep 0747  total reward: -2157.3802366566347
  Simulating cascading failure
  ok
timestep 0748  total reward: -2160.2375500542107
  Simulating cascading failure
  ok
timestep 0749  total reward: -2163.1591717698193
  Simulating cascading failure
  ok
timestep 0750  total reward: -2166.4184956919344
  Simulating cascading failure
  ok
timestep 0751  total reward: -2171.692207033615
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0752  total reward: -2185.692207033615
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0753  total reward: -2191.7598718266286
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0754  total reward: -2205.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0755  total reward: -2219.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0756  total reward: -2233.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0757  total reward: -2247.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0758  total reward: -2261.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0759  total reward: -2275.7598718266286
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0760  total reward: -2280.938900823795
  Simulating cascading failure
  ok
timestep 0761  total reward: -2286.009565753611
  Simulating cascading failure
  ok
timestep 0762  total reward: -2291.5209784713484
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0763  total reward: -2305.5209784713484
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0764  total reward: -2319.5209784713484
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0765  total reward: -2324.4778635412727
  Simulating cascading failure
  ok
timestep 0766  total reward: -2329.113934136166
  Simulating cascading failure
  ok
timestep 0767  total reward: -2333.663805261023
  Simulating cascading failure
  ok
timestep 0768  total reward: -2338.537701372573
  Simulating cascading failure
  ok
timestep 0769  total reward: -2342.713669011816
  Simulating cascading failure
  ok
timestep 0770  total reward: -2345.7421385289836
  Simulating cascading failure
  ok
timestep 0771  total reward: -2348.193619354376
  Simulating cascading failure
  ok
timestep 0772  total reward: -2349.745459439533
  Simulating cascading failure
  ok
timestep 0773  total reward: -2351.4900947634083
  Simulating cascading failure
  ok
timestep 0774  total reward: -2354.4985198394043
  Simulating cascading failure
  ok
timestep 0775  total reward: -2358.6820384601924
  Simulating cascading failure
  ok
timestep 0776  total reward: -2363.255580086193
  Simulating cascading failure
  ok
timestep 0777  total reward: -2368.2065861614765
  Simulating cascading failure
  ok
timestep 0778  total reward: -2374.327207582293
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0779  total reward: -2388.327207582293
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0780  total reward: -2402.327207582293
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0781  total reward: -2409.1516124676004
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0782  total reward: -2423.1516124676004
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0783  total reward: -2427.854577807502
  Simulating cascading failure
  ok
timestep 0784  total reward: -2433.202198739573
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0785  total reward: -2447.202198739573
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0786  total reward: -2452.1450499647926
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0787  total reward: -2466.1450499647926
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0788  total reward: -2480.1450499647926
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0789  total reward: -2484.7609134083605
  Simulating cascading failure
  ok
timestep 0790  total reward: -2488.915465379064
  Simulating cascading failure
  ok
timestep 0791  total reward: -2493.101934220557
  Simulating cascading failure
  ok
timestep 0792  total reward: -2497.321799087932
  Simulating cascading failure
  ok
timestep 0793  total reward: -2500.518070824613
  Simulating cascading failure
  ok
timestep 0794  total reward: -2502.4114740214104
  Simulating cascading failure
  ok
timestep 0795  total reward: -2504.1855779224175
  Simulating cascading failure
  ok
timestep 0796  total reward: -2505.805612687126
  Simulating cascading failure
  ok
timestep 0797  total reward: -2507.3906745839295
  Simulating cascading failure
  ok
timestep 0798  total reward: -2509.678982838712
  Simulating cascading failure
  ok
timestep 0799  total reward: -2511.9061541414294
  Simulating cascading failure
  ok
timestep 0800  total reward: -2514.308271115417
  Simulating cascading failure
  ok
timestep 0801  total reward: -2518.565337552047
  Simulating cascading failure
  ok
timestep 0802  total reward: -2523.8441551321357
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0803  total reward: -2537.8441551321357
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0804  total reward: -2542.281891125307
  Simulating cascading failure
  ok
timestep 0805  total reward: -2546.416958402441
  Simulating cascading failure
  ok
timestep 0806  total reward: -2550.110228769617
  Simulating cascading failure
  ok
timestep 0807  total reward: -2553.131336130393
  Simulating cascading failure
  ok
timestep 0808  total reward: -2555.9605054190015
  Simulating cascading failure
  ok
timestep 0809  total reward: -2559.1926762517896
  Simulating cascading failure
  ok
timestep 0810  total reward: -2563.0890531714867
  Simulating cascading failure
  ok
timestep 0811  total reward: -2567.103305810012
  Simulating cascading failure
  ok
timestep 0812  total reward: -2571.3141066315447
  Simulating cascading failure
  ok
timestep 0813  total reward: -2575.109072158282
  Simulating cascading failure
  ok
timestep 0814  total reward: -2578.2681274197766
  Simulating cascading failure
  ok
timestep 0815  total reward: -2581.572918959281
  Simulating cascading failure
  ok
timestep 0816  total reward: -2584.078666333784
  Simulating cascading failure
  ok
timestep 0817  total reward: -2586.066303415705
  Simulating cascading failure
  ok
timestep 0818  total reward: -2587.7349880417287
  Simulating cascading failure
  ok
timestep 0819  total reward: -2589.238785365083
  Simulating cascading failure
  ok
timestep 0820  total reward: -2590.7574664594804
  Simulating cascading failure
  ok
timestep 0821  total reward: -2592.1108233174446
  Simulating cascading failure
  ok
timestep 0822  total reward: -2593.761552984757
  Simulating cascading failure
  ok
timestep 0823  total reward: -2595.8849518636325
  Simulating cascading failure
  ok
timestep 0824  total reward: -2598.3549676264356
  Simulating cascading failure
  ok
timestep 0825  total reward: -2602.0328740956415
  Simulating cascading failure
  ok
timestep 0826  total reward: -2605.976115552507
  Simulating cascading failure
  ok
timestep 0827  total reward: -2609.5403164885297
  Simulating cascading failure
  ok
timestep 0828  total reward: -2612.964586919492
  Simulating cascading failure
  ok
timestep 0829  total reward: -2616.0565525187867
  Simulating cascading failure
  ok
timestep 0830  total reward: -2619.188505404127
  Simulating cascading failure
  ok
timestep 0831  total reward: -2621.8971359254037
  Simulating cascading failure
  ok
timestep 0832  total reward: -2624.2598628517367
  Simulating cascading failure
  ok
timestep 0833  total reward: -2626.7253095105393
  Simulating cascading failure
  ok
timestep 0834  total reward: -2629.8904487141763
  Simulating cascading failure
  ok
timestep 0835  total reward: -2632.605451998738
  Simulating cascading failure
  ok
timestep 0836  total reward: -2634.6949433704303
  Simulating cascading failure
  ok
timestep 0837  total reward: -2637.122253082835
  Simulating cascading failure
  ok
timestep 0838  total reward: -2639.5384807161736
  Simulating cascading failure
  ok
timestep 0839  total reward: -2642.469359535341
  Simulating cascading failure
  ok
timestep 0840  total reward: -2645.917344802013
  Simulating cascading failure
  ok
timestep 0841  total reward: -2649.0627422869293
  Simulating cascading failure
  ok
timestep 0842  total reward: -2651.912139397
  Simulating cascading failure
  ok
timestep 0843  total reward: -2654.4990837399046
  Simulating cascading failure
  ok
timestep 0844  total reward: -2656.6484574372535
  Simulating cascading failure
  ok
timestep 0845  total reward: -2658.812048924281
  Simulating cascading failure
  ok
timestep 0846  total reward: -2661.6903369513343
  Simulating cascading failure
  ok
timestep 0847  total reward: -2665.4796121043228
  Simulating cascading failure
  ok
timestep 0848  total reward: -2669.859448328
  Simulating cascading failure
  ok
timestep 0849  total reward: -2674.616051605652
  Simulating cascading failure
  ok
timestep 0850  total reward: -2680.0607950108088
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0851  total reward: -2694.0607950108088
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0852  total reward: -2700.607651686856
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0853  total reward: -2714.607651686856
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0854  total reward: -2728.607651686856
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0855  total reward: -2733.0840646674374
  Simulating cascading failure
  ok
timestep 0856  total reward: -2737.391593813638
  Simulating cascading failure
  ok
timestep 0857  total reward: -2742.5449490350834
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0858  total reward: -2756.5449490350834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0859  total reward: -2761.7975886410145
  Simulating cascading failure
  ok
timestep 0860  total reward: -2768.0019741412025
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0861  total reward: -2782.0019741412025
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0862  total reward: -2785.9028034822363
  Simulating cascading failure
  ok
timestep 0863  total reward: -2790.034195626548
  Simulating cascading failure
  ok
timestep 0864  total reward: -2794.1368428607693
  Simulating cascading failure
  ok
timestep 0865  total reward: -2797.9116951266724
  Simulating cascading failure
  ok
timestep 0866  total reward: -2801.2251873800915
  Simulating cascading failure
  ok
timestep 0867  total reward: -2804.093627958602
  Simulating cascading failure
  ok
timestep 0868  total reward: -2806.7562635449467
  Simulating cascading failure
  ok
timestep 0869  total reward: -2809.3489839955355
  Simulating cascading failure
  ok
timestep 0870  total reward: -2812.582313230426
  Simulating cascading failure
  ok
timestep 0871  total reward: -2816.968845997466
  Simulating cascading failure
  ok
timestep 0872  total reward: -2822.201647625341
  Simulating cascading failure
  ok
timestep 0873  total reward: -2828.716735083423
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0874  total reward: -2842.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0875  total reward: -2856.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0876  total reward: -2870.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0877  total reward: -2884.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0878  total reward: -2898.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0879  total reward: -2912.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0880  total reward: -2926.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0881  total reward: -2940.716735083423
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0882  total reward: -2947.2166072207683
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0883  total reward: -2961.2166072207683
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0884  total reward: -2967.0841090775525
  Simulating cascading failure
  ok
timestep 0885  total reward: -2971.8519377094485
  Simulating cascading failure
  ok
timestep 0886  total reward: -2976.3909063886126
  Simulating cascading failure
  ok
timestep 0887  total reward: -2981.435282008542
  Simulating cascading failure
  ok
timestep 0888  total reward: -2985.9148357075446
  Simulating cascading failure
  ok
timestep 0889  total reward: -2989.850826704019
  Simulating cascading failure
  ok
timestep 0890  total reward: -2993.822912102459
  Simulating cascading failure
  ok
timestep 0891  total reward: -2997.007780410875
  Simulating cascading failure
  ok
timestep 0892  total reward: -2999.2939443894816
  Simulating cascading failure
  ok
timestep 0893  total reward: -3001.9157418059917
  Simulating cascading failure
  ok
timestep 0894  total reward: -3005.689119027651
  Simulating cascading failure
  ok
timestep 0895  total reward: -3010.4386414887877
  Simulating cascading failure
  ok
timestep 0896  total reward: -3015.9206425785387
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0897  total reward: -3029.9206425785387
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0898  total reward: -3043.9206425785387
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0899  total reward: -3049.985986845795
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0900  total reward: -3063.985986845795
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0901  total reward: -3077.985986845795
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0902  total reward: -3083.8982968046166
  Simulating cascading failure
  ok
timestep 0903  total reward: -3089.275959970166
  Simulating cascading failure
  ok
timestep 0904  total reward: -3095.415352974609
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0905  total reward: -3109.415352974609
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0906  total reward: -3115.8467506096813
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0907  total reward: -3129.8467506096813
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0908  total reward: -3143.8467506096813
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0909  total reward: -3157.8467506096813
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0910  total reward: -3162.9947868451864
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0911  total reward: -3176.9947868451864
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0912  total reward: -3182.0274065403796
  Simulating cascading failure
  ok
timestep 0913  total reward: -3186.0307686172664
  Simulating cascading failure
  ok
timestep 0914  total reward: -3189.2018780922085
  Simulating cascading failure
  ok
timestep 0915  total reward: -3192.061700994751
  Simulating cascading failure
  ok
timestep 0916  total reward: -3194.763308701909
  Simulating cascading failure
  ok
timestep 0917  total reward: -3197.4144200692867
  Simulating cascading failure
  ok
timestep 0918  total reward: -3200.4672231081686
  Simulating cascading failure
  ok
timestep 0919  total reward: -3204.6601080908395
  Simulating cascading failure
  ok
timestep 0920  total reward: -3209.762769116753
  Simulating cascading failure
  ok
timestep 0921  total reward: -3216.211232577536
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0922  total reward: -3230.211232577536
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0923  total reward: -3244.211232577536
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0924  total reward: -3258.211232577536
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0925  total reward: -3272.211232577536
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0926  total reward: -3286.211232577536
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0927  total reward: -3291.75886896846
  Simulating cascading failure
  ok
timestep 0928  total reward: -3296.8409855975647
  Simulating cascading failure
  ok
timestep 0929  total reward: -3301.5862195934556
  Simulating cascading failure
  ok
timestep 0930  total reward: -3306.858076349215
  Simulating cascading failure
  ok
timestep 0931  total reward: -3313.4267386544407
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0932  total reward: -3327.4267386544407
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0933  total reward: -3332.029434271849
  Simulating cascading failure
  ok
timestep 0934  total reward: -3337.0782694810937
  Simulating cascading failure
  ok
timestep 0935  total reward: -3342.399090315167
  Simulating cascading failure
  ok
timestep 0936  total reward: -3347.698939158715
  Simulating cascading failure
  ok
timestep 0937  total reward: -3353.448576074418
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0938  total reward: -3367.448576074418
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0939  total reward: -3370.075785845225
  Simulating cascading failure
  ok
timestep 0940  total reward: -3372.3820115238914
  Simulating cascading failure
  ok
timestep 0941  total reward: -3375.153598746146
  Simulating cascading failure
  ok
timestep 0942  total reward: -3378.448576409068
  Simulating cascading failure
  ok
timestep 0943  total reward: -3382.493270453686
  Simulating cascading failure
  ok
timestep 0944  total reward: -3387.255038725305
  Simulating cascading failure
  ok
timestep 0945  total reward: -3392.4033762035306
  Simulating cascading failure
  ok
timestep 0946  total reward: -3397.951111741244
  Simulating cascading failure
  ok
timestep 0947  total reward: -3403.7817707022014
  Simulating cascading failure
  ok
timestep 0948  total reward: -3409.95791872564
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0949  total reward: -3423.95791872564
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0950  total reward: -3437.95791872564
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0951  total reward: -3443.180155475647
  Simulating cascading failure
  ok
timestep 0952  total reward: -3447.6921645870752
  Simulating cascading failure
  ok
timestep 0953  total reward: -3452.052365817862
  Simulating cascading failure
  ok
timestep 0954  total reward: -3457.746582987608
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0955  total reward: -3471.746582987608
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0956  total reward: -3485.746582987608
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0957  total reward: -3490.6660154578312
  Simulating cascading failure
  ok
timestep 0958  total reward: -3495.487888158158
  Simulating cascading failure
  ok
timestep 0959  total reward: -3499.9150279330106
  Simulating cascading failure
  ok
timestep 0960  total reward: -3502.881680832711
  Simulating cascading failure
  ok
timestep 0961  total reward: -3505.0592525776638
  Simulating cascading failure
  ok
timestep 0962  total reward: -3507.0631394411384
  Simulating cascading failure
  ok
timestep 0963  total reward: -3508.6612263998327
  Simulating cascading failure
  ok
timestep 0964  total reward: -3510.1743752027987
  Simulating cascading failure
  ok
timestep 0965  total reward: -3511.8119750974715
  Simulating cascading failure
  ok
timestep 0966  total reward: -3513.8621285856384
  Simulating cascading failure
  ok
timestep 0967  total reward: -3516.464705180231
  Simulating cascading failure
  ok
timestep 0968  total reward: -3519.48534357964
  Simulating cascading failure
  ok
timestep 0969  total reward: -3523.0093342781965
  Simulating cascading failure
  ok
timestep 0970  total reward: -3527.077184518802
  Simulating cascading failure
  ok
timestep 0971  total reward: -3531.2122150753635
  Simulating cascading failure
  ok
timestep 0972  total reward: -3535.545487439354
  Simulating cascading failure
  ok
timestep 0973  total reward: -3540.035652189153
  Simulating cascading failure
  ok
timestep 0974  total reward: -3545.2117480235975
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0975  total reward: -3559.2117480235975
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0976  total reward: -3562.9641029255845
  Simulating cascading failure
  ok
timestep 0977  total reward: -3566.2343227314827
  Simulating cascading failure
  ok
timestep 0978  total reward: -3569.9652062019954
  Simulating cascading failure
  ok
timestep 0979  total reward: -3573.8129401375636
  Simulating cascading failure
  ok
timestep 0980  total reward: -3577.623749531764
  Simulating cascading failure
  ok
timestep 0981  total reward: -3581.697844135936
  Simulating cascading failure
  ok
timestep 0982  total reward: -3585.2457948113097
  Simulating cascading failure
  ok
timestep 0983  total reward: -3588.3212281267824
  Simulating cascading failure
  ok
timestep 0984  total reward: -3590.507105643784
  Simulating cascading failure
  ok
timestep 0985  total reward: -3591.838727163565
  Simulating cascading failure
  ok
timestep 0986  total reward: -3593.307368667155
  Simulating cascading failure
  ok
timestep 0987  total reward: -3594.574911079095
  Simulating cascading failure
  ok
timestep 0988  total reward: -3595.714468537734
  Simulating cascading failure
  ok
timestep 0989  total reward: -3597.0289764202794
  Simulating cascading failure
  ok
timestep 0990  total reward: -3598.579545400458
  Simulating cascading failure
  ok
timestep 0991  total reward: -3599.894444712334
  Simulating cascading failure
  ok
timestep 0992  total reward: -3601.929633121274
  Simulating cascading failure
  ok
timestep 0993  total reward: -3604.856069786953
  Simulating cascading failure
  ok
timestep 0994  total reward: -3607.811907234894
  Simulating cascading failure
  ok
timestep 0995  total reward: -3611.078150497959
  Simulating cascading failure
  ok
timestep 0996  total reward: -3614.382396819343
  Simulating cascading failure
  ok
timestep 0997  total reward: -3617.3535319637936
  Simulating cascading failure
  ok
timestep 0998  total reward: -3620.2262830368463
  Simulating cascading failure
  ok
timestep 0999  total reward: -3623.0292176370563
  Simulating cascading failure
  ok
timestep 1000  total reward: -3625.547119319724
  Simulating cascading failure
  ok
timestep 1001  total reward: -3628.1534940351835
  Simulating cascading failure
  ok
timestep 1002  total reward: -3631.1078377693498
  Simulating cascading failure
  ok
timestep 1003  total reward: -3634.059079540061
  Simulating cascading failure
  ok
timestep 1004  total reward: -3636.733202148626
  Simulating cascading failure
  ok
timestep 1005  total reward: -3639.1280613035674
  Simulating cascading failure
  ok
timestep 1006  total reward: -3641.472297859979
  Simulating cascading failure
  ok
timestep 1007  total reward: -3643.8464166931835
  Simulating cascading failure
  ok
timestep 1008  total reward: -3646.447287682887
  Simulating cascading failure
  ok
timestep 1009  total reward: -3649.451347177287
  Simulating cascading failure
  ok
timestep 1010  total reward: -3652.3326228232827
  Simulating cascading failure
  ok
timestep 1011  total reward: -3654.671182810737
  Simulating cascading failure
  ok
timestep 1012  total reward: -3656.7927620410173
  Simulating cascading failure
  ok
timestep 1013  total reward: -3659.3599871639203
  Simulating cascading failure
  ok
timestep 1014  total reward: -3662.427019339458
  Simulating cascading failure
  ok
timestep 1015  total reward: -3666.045454618009
  Simulating cascading failure
  ok
timestep 1016  total reward: -3670.269657866453
  Simulating cascading failure
  ok
timestep 1017  total reward: -3675.0463917067664
  Simulating cascading failure
  ok
timestep 1018  total reward: -3680.9987201473555
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1019  total reward: -3694.9987201473555
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1020  total reward: -3700.9323500870382
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1021  total reward: -3714.9323500870382
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1022  total reward: -3728.9323500870382
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1023  total reward: -3733.167952280169
  Simulating cascading failure
  ok
timestep 1024  total reward: -3737.382853046938
  Simulating cascading failure
  ok
timestep 1025  total reward: -3741.6539516914627
  Simulating cascading failure
  ok
timestep 1026  total reward: -3746.078471094166
  Simulating cascading failure
  ok
timestep 1027  total reward: -3752.0714408079384
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1028  total reward: -3766.0714408079393
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1029  total reward: -3771.140620008182
  Simulating cascading failure
  ok
timestep 1030  total reward: -3776.083217201365
  Simulating cascading failure
  ok
timestep 1031  total reward: -3780.2288013892976
  Simulating cascading failure
  ok
timestep 1032  total reward: -3784.312276702657
  Simulating cascading failure
  ok
timestep 1033  total reward: -3788.8198772176374
  Simulating cascading failure
  ok
timestep 1034  total reward: -3792.9039032957344
  Simulating cascading failure
  ok
timestep 1035  total reward: -3795.574612501433
  Simulating cascading failure
  ok
timestep 1036  total reward: -3797.3670125180706
  Simulating cascading failure
  ok
timestep 1037  total reward: -3799.272339668906
  Simulating cascading failure
  ok
timestep 1038  total reward: -3803.1011825108017
  Simulating cascading failure
  ok
timestep 1039  total reward: -3808.6791104089207
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1040  total reward: -3822.679110408921
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1041  total reward: -3836.679110408921
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1042  total reward: -3843.3814637306814
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1043  total reward: -3857.3814637306814
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1044  total reward: -3871.3814637306814
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1045  total reward: -3885.3814637306814
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1046  total reward: -3899.3814637306814
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1047  total reward: -3913.3814637306814
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1048  total reward: -3919.3533894277834
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1049  total reward: -3933.3533894277834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1050  total reward: -3939.0697607650372
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1051  total reward: -3953.0697607650372
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1052  total reward: -3967.0697607650372
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1053  total reward: -3972.3374327132865
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1054  total reward: -3986.3374327132865
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1055  total reward: -3990.951731456317
  Simulating cascading failure
  ok
timestep 1056  total reward: -3995.342664878902
  Simulating cascading failure
  ok
timestep 1057  total reward: -3999.1865870515576
  Simulating cascading failure
  ok
timestep 1058  total reward: -4002.2497030448085
  Simulating cascading failure
  ok
timestep 1059  total reward: -4004.8806761491633
  Simulating cascading failure
  ok
timestep 1060  total reward: -4007.539961565217
  Simulating cascading failure
  ok
timestep 1061  total reward: -4010.564774932446
  Simulating cascading failure
  ok
timestep 1062  total reward: -4014.4893207569885
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1063  total reward: -4028.4893207569885
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1064  total reward: -4034.7912552564194
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1065  total reward: -4048.7912552564194
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1066  total reward: -4062.7912552564194
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1067  total reward: -4076.7912552564194
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1068  total reward: -4090.7912552564194
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1069  total reward: -4104.791255256419
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1070  total reward: -4118.791255256419
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1071  total reward: -4124.179726303318
  Simulating cascading failure
  ok
timestep 1072  total reward: -4129.5830077647
  Simulating cascading failure
  ok
timestep 1073  total reward: -4134.774053529455
  Simulating cascading failure
  ok
timestep 1074  total reward: -4140.0739290516685
  Simulating cascading failure
  ok
timestep 1075  total reward: -4145.932122311991
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1076  total reward: -4159.932122311991
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1077  total reward: -4167.243141003521
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1078  total reward: -4181.243141003521
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1079  total reward: -4186.254383350148
  Simulating cascading failure
  ok
timestep 1080  total reward: -4190.775381767166
  Simulating cascading failure
  ok
timestep 1081  total reward: -4194.305737301866
  Simulating cascading failure
  ok
timestep 1082  total reward: -4197.203451437385
  Simulating cascading failure
  ok
timestep 1083  total reward: -4199.694248851868
  Simulating cascading failure
  ok
timestep 1084  total reward: -4202.024436315222
  Simulating cascading failure
  ok
timestep 1085  total reward: -4204.5601630704
  Simulating cascading failure
  ok
timestep 1086  total reward: -4206.852977946275
  Simulating cascading failure
  ok
timestep 1087  total reward: -4210.321170987087
  Simulating cascading failure
  ok
timestep 1088  total reward: -4215.549002208693
  Simulating cascading failure
  ok
timestep 1089  total reward: -4221.251516956733
  Simulating cascading failure
  ok
timestep 1090  total reward: -4227.730198872717
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1091  total reward: -4241.730198872717
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1092  total reward: -4255.730198872717
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1093  total reward: -4269.730198872717
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1094  total reward: -4283.730198872717
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1095  total reward: -4297.730198872717
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1096  total reward: -4302.650572018049
  Simulating cascading failure
  ok
timestep 1097  total reward: -4307.902549293333
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1098  total reward: -4321.902549293333
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1099  total reward: -4335.902549293333
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1100  total reward: -4349.902549293333
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1101  total reward: -4354.7446549799715
  Simulating cascading failure
  ok
timestep 1102  total reward: -4360.092644051854
  Simulating cascading failure
  ok
timestep 1103  total reward: -4365.6595689596115
  Simulating cascading failure
  ok
timestep 1104  total reward: -4370.678209902542
  Simulating cascading failure
  ok
timestep 1105  total reward: -4374.568075967465
  Simulating cascading failure
  ok
timestep 1106  total reward: -4377.5512154642
  Simulating cascading failure
  ok
timestep 1107  total reward: -4379.82878961307
  Simulating cascading failure
  ok
timestep 1108  total reward: -4381.809488202596
  Simulating cascading failure
  ok
timestep 1109  total reward: -4384.216164185296
  Simulating cascading failure
  ok
timestep 1110  total reward: -4387.145460172971
  Simulating cascading failure
  ok
timestep 1111  total reward: -4391.247759845699
  Simulating cascading failure
  ok
timestep 1112  total reward: -4396.300598557262
  Simulating cascading failure
  ok
timestep 1113  total reward: -4401.434187443287
  Simulating cascading failure
  ok
timestep 1114  total reward: -4407.123737229042
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1115  total reward: -4421.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1116  total reward: -4435.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1117  total reward: -4449.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1118  total reward: -4463.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1119  total reward: -4477.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1120  total reward: -4491.123737229042
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1121  total reward: -4495.5342528927995
  Simulating cascading failure
  ok
timestep 1122  total reward: -4500.6633182161695
  Simulating cascading failure
  ok
timestep 1123  total reward: -4506.660187060257
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1124  total reward: -4520.660187060257
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1125  total reward: -4525.694839925609
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1126  total reward: -4539.694839925609
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1127  total reward: -4544.086038016237
  Simulating cascading failure
  ok
timestep 1128  total reward: -4547.751379178289
  Simulating cascading failure
  ok
timestep 1129  total reward: -4550.123708932271
  Simulating cascading failure
  ok
timestep 1130  total reward: -4551.987050269155
  Simulating cascading failure
  ok
timestep 1131  total reward: -4553.734769452068
  Simulating cascading failure
  ok
timestep 1132  total reward: -4555.296098124688
  Simulating cascading failure
  ok
timestep 1133  total reward: -4557.005915457528
  Simulating cascading failure
  ok
timestep 1134  total reward: -4559.126252148697
  Simulating cascading failure
  ok
timestep 1135  total reward: -4561.630557386491
  Simulating cascading failure
  ok
timestep 1136  total reward: -4564.77972376851
  Simulating cascading failure
  ok
timestep 1137  total reward: -4568.67292313546
  Simulating cascading failure
  ok
timestep 1138  total reward: -4572.402051008885
  Simulating cascading failure
  ok
timestep 1139  total reward: -4576.537300769493
  Simulating cascading failure
  ok
timestep 1140  total reward: -4583.088782935212
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1141  total reward: -4597.088782935212
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1142  total reward: -4601.030892139346
  Simulating cascading failure
  ok
timestep 1143  total reward: -4604.57111627065
  Simulating cascading failure
  ok
timestep 1144  total reward: -4607.56061508587
  Simulating cascading failure
  ok
timestep 1145  total reward: -4610.59752694569
  Simulating cascading failure
  ok
timestep 1146  total reward: -4614.330819199237
  Simulating cascading failure
  ok
timestep 1147  total reward: -4618.2828442639275
  Simulating cascading failure
  ok
timestep 1148  total reward: -4621.816927710774
  Simulating cascading failure
  ok
timestep 1149  total reward: -4624.831074330028
  Simulating cascading failure
  ok
timestep 1150  total reward: -4627.076807224139
  Simulating cascading failure
  ok
timestep 1151  total reward: -4629.59309486432
  Simulating cascading failure
  ok
timestep 1152  total reward: -4632.85956288691
  Simulating cascading failure
  ok
timestep 1153  total reward: -4635.291135883338
  Simulating cascading failure
  ok
timestep 1154  total reward: -4636.751424929784
  Simulating cascading failure
  ok
timestep 1155  total reward: -4638.027970237082
  Simulating cascading failure
  ok
timestep 1156  total reward: -4639.262763231014
  Simulating cascading failure
  ok
timestep 1157  total reward: -4640.586120448764
  Simulating cascading failure
  ok
timestep 1158  total reward: -4642.131196737732
  Simulating cascading failure
  ok
timestep 1159  total reward: -4644.535005066383
  Simulating cascading failure
  ok
timestep 1160  total reward: -4647.615791825672
  Simulating cascading failure
  ok
timestep 1161  total reward: -4649.995763233105
  Simulating cascading failure
  ok
timestep 1162  total reward: -4651.713133964235
  Simulating cascading failure
  ok
timestep 1163  total reward: -4654.145004514515
  Simulating cascading failure
  ok
timestep 1164  total reward: -4657.4624968123735
  Simulating cascading failure
  ok
timestep 1165  total reward: -4661.768611192566
  Simulating cascading failure
  ok
timestep 1166  total reward: -4665.771954755297
  Simulating cascading failure
  ok
timestep 1167  total reward: -4669.283794034915
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1168  total reward: -4683.2837940349145
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1169  total reward: -4685.718689151369
  Simulating cascading failure
  ok
timestep 1170  total reward: -4688.33747022309
  Simulating cascading failure
  ok
timestep 1171  total reward: -4691.59853101574
  Simulating cascading failure
  ok
timestep 1172  total reward: -4694.592593841511
  Simulating cascading failure
  ok
timestep 1173  total reward: -4696.9664859237055
  Simulating cascading failure
  ok
timestep 1174  total reward: -4699.2597018436445
  Simulating cascading failure
  ok
timestep 1175  total reward: -4701.612014273391
  Simulating cascading failure
  ok
timestep 1176  total reward: -4704.560001835401
  Simulating cascading failure
  ok
timestep 1177  total reward: -4707.785456238714
  Simulating cascading failure
  ok
timestep 1178  total reward: -4710.522297359081
  Simulating cascading failure
  ok
timestep 1179  total reward: -4712.793008816983
  Simulating cascading failure
  ok
timestep 1180  total reward: -4714.815717744404
  Simulating cascading failure
  ok
timestep 1181  total reward: -4717.009388418222
  Simulating cascading failure
  ok
timestep 1182  total reward: -4719.826518626706
  Simulating cascading failure
  ok
timestep 1183  total reward: -4723.668174831537
  Simulating cascading failure
  ok
timestep 1184  total reward: -4728.476826933711
  Simulating cascading failure
  ok
timestep 1185  total reward: -4733.752893530835
  Simulating cascading failure
  ok
timestep 1186  total reward: -4739.581492605139
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1187  total reward: -4753.581492605139
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1188  total reward: -4767.581492605139
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1189  total reward: -4781.581492605139
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1190  total reward: -4786.339458644095
  Simulating cascading failure
  ok
timestep 1191  total reward: -4791.615178187045
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1192  total reward: -4805.615178187045
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1193  total reward: -4809.5170246723155
  Simulating cascading failure
  ok
timestep 1194  total reward: -4814.15922952628
  Simulating cascading failure
  ok
timestep 1195  total reward: -4819.990543785798
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1196  total reward: -4833.990543785798
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1197  total reward: -4838.700781611706
  Simulating cascading failure
  ok
timestep 1198  total reward: -4843.109269337774
  Simulating cascading failure
  ok
timestep 1199  total reward: -4847.755855542469
  Simulating cascading failure
  ok
timestep 1200  total reward: -4851.874184702203
  Simulating cascading failure
  ok
timestep 1201  total reward: -4855.258379565259
  Simulating cascading failure
  ok
timestep 1202  total reward: -4858.164065199234
  Simulating cascading failure
  ok
timestep 1203  total reward: -4861.018179698928
  Simulating cascading failure
  ok
timestep 1204  total reward: -4862.972433825456
  Simulating cascading failure
  ok
timestep 1205  total reward: -4864.91973537543
  Simulating cascading failure
  ok
timestep 1206  total reward: -4868.148982877425
  Simulating cascading failure
  ok
timestep 1207  total reward: -4872.665115701398
  Simulating cascading failure
  ok
timestep 1208  total reward: -4878.398314207332
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1209  total reward: -4892.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1210  total reward: -4906.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1211  total reward: -4920.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1212  total reward: -4934.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1213  total reward: -4948.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1214  total reward: -4962.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1215  total reward: -4976.398314207332
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1216  total reward: -4980.826943416572
  Simulating cascading failure
  ok
timestep 1217  total reward: -4986.696470901834
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1218  total reward: -5000.696470901834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1219  total reward: -5014.696470901834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1220  total reward: -5028.696470901834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1221  total reward: -5042.696470901834
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1222  total reward: -5047.642477921389
  Simulating cascading failure
  ok
timestep 1223  total reward: -5053.444444649665
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1224  total reward: -5067.444444649665
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1225  total reward: -5069.423181596615
  Simulating cascading failure
  ok
timestep 1226  total reward: -5071.040264729368
  Simulating cascading failure
  ok
timestep 1227  total reward: -5072.526693792276
  Simulating cascading failure
  ok
timestep 1228  total reward: -5073.986360418337
  Simulating cascading failure
  ok
timestep 1229  total reward: -5075.429843756506
  Simulating cascading failure
  ok
timestep 1230  total reward: -5077.167669267275
  Simulating cascading failure
  ok
timestep 1231  total reward: -5079.260360949145
  Simulating cascading failure
  ok
timestep 1232  total reward: -5081.731674017946
  Simulating cascading failure
  ok
timestep 1233  total reward: -5084.313025701061
  Simulating cascading failure
  ok
timestep 1234  total reward: -5086.84545991682
  Simulating cascading failure
  ok
timestep 1235  total reward: -5089.501524030104
  Simulating cascading failure
  ok
timestep 1236  total reward: -5092.037455629668
  Simulating cascading failure
  ok
timestep 1237  total reward: -5094.666029948474
  Simulating cascading failure
  ok
timestep 1238  total reward: -5098.109588607154
  Simulating cascading failure
  ok
timestep 1239  total reward: -5102.035851368772
  Simulating cascading failure
  ok
timestep 1240  total reward: -5105.221702528021
  Simulating cascading failure
  ok
timestep 1241  total reward: -5107.66600288824
  Simulating cascading failure
  ok
timestep 1242  total reward: -5110.024525116293
  Simulating cascading failure
  ok
timestep 1243  total reward: -5112.545536051073
  Simulating cascading failure
  ok
timestep 1244  total reward: -5114.814245986461
  Simulating cascading failure
  ok
timestep 1245  total reward: -5117.843290041941
  Simulating cascading failure
  ok
timestep 1246  total reward: -5122.392628353322
  Simulating cascading failure
  ok
timestep 1247  total reward: -5128.306942037851
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1248  total reward: -5142.30694203785
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1249  total reward: -5156.30694203785
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1250  total reward: -5170.30694203785
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1251  total reward: -5184.30694203785
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1252  total reward: -5190.031367221829
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1253  total reward: -5204.031367221829
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1254  total reward: -5208.9230586400845
  Simulating cascading failure
  ok
timestep 1255  total reward: -5213.623062302355
  Simulating cascading failure
  ok
timestep 1256  total reward: -5218.714580536836
  Simulating cascading failure
  ok
timestep 1257  total reward: -5224.486512837145
  Simulating cascading failure
  ok
timestep 1258  total reward: -5230.891057226058
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1259  total reward: -5244.891057226058
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1260  total reward: -5249.522104860925
  Simulating cascading failure
  ok
timestep 1261  total reward: -5253.35265406737
  Simulating cascading failure
  ok
timestep 1262  total reward: -5256.878927604535
  Simulating cascading failure
  ok
timestep 1263  total reward: -5260.487697277031
  Simulating cascading failure
  ok
timestep 1264  total reward: -5263.515591021063
  Simulating cascading failure
  ok
timestep 1265  total reward: -5266.1366858510855
  Simulating cascading failure
  ok
timestep 1266  total reward: -5268.42837532079
  Simulating cascading failure
  ok
timestep 1267  total reward: -5270.883034845374
  Simulating cascading failure
  ok
timestep 1268  total reward: -5273.985481831992
  Simulating cascading failure
  ok
timestep 1269  total reward: -5278.595301677216
  Simulating cascading failure
  ok
timestep 1270  total reward: -5284.322225577701
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1271  total reward: -5298.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1272  total reward: -5312.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1273  total reward: -5326.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1274  total reward: -5340.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1275  total reward: -5354.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1276  total reward: -5368.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1277  total reward: -5382.322225577701
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1278  total reward: -5386.868562492722
  Simulating cascading failure
  ok
timestep 1279  total reward: -5391.331412713038
  Simulating cascading failure
  ok
timestep 1280  total reward: -5396.218764941541
  Simulating cascading failure
  ok
timestep 1281  total reward: -5401.3507409562935
  Simulating cascading failure
  ok
timestep 1282  total reward: -5406.296475554658
  Simulating cascading failure
  ok
timestep 1283  total reward: -5411.769299774513
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1284  total reward: -5425.769299774513
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1285  total reward: -5439.769299774513
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1286  total reward: -5453.769299774513
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1287  total reward: -5456.053264696609
  Simulating cascading failure
  ok
timestep 1288  total reward: -5457.987287778478
  Simulating cascading failure
  ok
timestep 1289  total reward: -5459.594151592988
  Simulating cascading failure
  ok
timestep 1290  total reward: -5461.175880675066
  Simulating cascading failure
  ok
timestep 1291  total reward: -5462.83004690118
  Simulating cascading failure
  ok
timestep 1292  total reward: -5464.9083313832125
  Simulating cascading failure
  ok
timestep 1293  total reward: -5467.659574564629
  Simulating cascading failure
  ok
timestep 1294  total reward: -5471.098285863031
  Simulating cascading failure
  ok
timestep 1295  total reward: -5475.339826550611
  Simulating cascading failure
  ok
timestep 1296  total reward: -5479.522989837149
  Simulating cascading failure
  ok
timestep 1297  total reward: -5483.668281979796
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1298  total reward: -5497.668281979796
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1299  total reward: -5502.430109280663
  Simulating cascading failure
  ok
timestep 1300  total reward: -5507.415100458724
  Simulating cascading failure
  ok
timestep 1301  total reward: -5511.258077790978
  Simulating cascading failure
  ok
timestep 1302  total reward: -5515.078620806626
  Simulating cascading failure
  ok
timestep 1303  total reward: -5519.181329316601
  Simulating cascading failure
  ok
timestep 1304  total reward: -5522.950446119678
  Simulating cascading failure
  ok
timestep 1305  total reward: -5527.412338732117
  Simulating cascading failure
  ok
timestep 1306  total reward: -5531.8933524404665
  Simulating cascading failure
  ok
timestep 1307  total reward: -5535.32515444014
  Simulating cascading failure
  ok
timestep 1308  total reward: -5538.210321185758
  Simulating cascading failure
  ok
timestep 1309  total reward: -5541.022242215934
  Simulating cascading failure
  ok
timestep 1310  total reward: -5543.387564177749
  Simulating cascading failure
  ok
timestep 1311  total reward: -5545.201106417301
  Simulating cascading failure
  ok
timestep 1312  total reward: -5546.915525869841
  Simulating cascading failure
  ok
timestep 1313  total reward: -5548.264529009221
  Simulating cascading failure
  ok
timestep 1314  total reward: -5549.154932813701
  Simulating cascading failure
  ok
timestep 1315  total reward: -5550.163597238753
  Simulating cascading failure
  ok
timestep 1316  total reward: -5551.723103229203
  Simulating cascading failure
  ok
timestep 1317  total reward: -5553.846009221843
  Simulating cascading failure
  ok
timestep 1318  total reward: -5556.37759304821
  Simulating cascading failure
  ok
timestep 1319  total reward: -5559.121774848838
  Simulating cascading failure
  ok
timestep 1320  total reward: -5562.417227854759
  Simulating cascading failure
  ok
timestep 1321  total reward: -5565.989057621311
  Simulating cascading failure
  ok
timestep 1322  total reward: -5569.431171882334
  Simulating cascading failure
  ok
timestep 1323  total reward: -5572.6124085210995
  Simulating cascading failure
  ok
timestep 1324  total reward: -5575.8575717767235
  Simulating cascading failure
  ok
timestep 1325  total reward: -5578.878232250825
  Simulating cascading failure
  ok
timestep 1326  total reward: -5581.279515216176
  Simulating cascading failure
  ok
timestep 1327  total reward: -5583.727808322016
  Simulating cascading failure
  ok
timestep 1328  total reward: -5587.039598265683
  Simulating cascading failure
  ok
timestep 1329  total reward: -5590.812691551964
  Simulating cascading failure
  ok
timestep 1330  total reward: -5594.4350259774765
  Simulating cascading failure
  ok
timestep 1331  total reward: -5597.438457973629
  Simulating cascading failure
  ok
timestep 1332  total reward: -5599.980925761225
  Simulating cascading failure
  ok
timestep 1333  total reward: -5602.696570478367
  Simulating cascading failure
  ok
timestep 1334  total reward: -5608.380370724657
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1335  total reward: -5622.380370724657
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1336  total reward: -5625.0860413696755
  Simulating cascading failure
  ok
timestep 1337  total reward: -5627.565393259685
  Simulating cascading failure
  ok
timestep 1338  total reward: -5629.74358271973
  Simulating cascading failure
  ok
timestep 1339  total reward: -5631.8584719656155
  Simulating cascading failure
  ok
timestep 1340  total reward: -5634.506797058955
  Simulating cascading failure
  ok
timestep 1341  total reward: -5638.458674751675
  Simulating cascading failure
  ok
timestep 1342  total reward: -5643.177919331529
  Simulating cascading failure
  ok
timestep 1343  total reward: -5648.177067552011
  Simulating cascading failure
  ok
timestep 1344  total reward: -5655.029238447902
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1345  total reward: -5669.029238447902
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1346  total reward: -5683.029238447902
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1347  total reward: -5689.029979281327
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1348  total reward: -5703.029979281326
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1349  total reward: -5708.347052046442
  Simulating cascading failure
  ok
timestep 1350  total reward: -5713.616750802193
  Simulating cascading failure
  ok
timestep 1351  total reward: -5718.647612869549
  Simulating cascading failure
  ok
timestep 1352  total reward: -5723.705033512126
  Simulating cascading failure
  ok
timestep 1353  total reward: -5728.685683971682
  Simulating cascading failure
  ok
timestep 1354  total reward: -5733.617153598225
  Simulating cascading failure
  ok
timestep 1355  total reward: -5738.414080298349
  Simulating cascading failure
  ok
timestep 1356  total reward: -5742.656916268843
  Simulating cascading failure
  ok
timestep 1357  total reward: -5746.266758486011
  Simulating cascading failure
  ok
timestep 1358  total reward: -5749.970365796525
  Simulating cascading failure
  ok
timestep 1359  total reward: -5754.324750882761
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1360  total reward: -5768.324750882761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1361  total reward: -5770.993798654176
  Simulating cascading failure
  ok
timestep 1362  total reward: -5773.432389575881
  Simulating cascading failure
  ok
timestep 1363  total reward: -5775.946141766235
  Simulating cascading failure
  ok
timestep 1364  total reward: -5779.0215107841095
  Simulating cascading failure
  ok
timestep 1365  total reward: -5784.50612214305
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1366  total reward: -5798.50612214305
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1367  total reward: -5804.040235953891
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1368  total reward: -5818.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1369  total reward: -5832.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1370  total reward: -5846.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1371  total reward: -5860.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1372  total reward: -5874.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1373  total reward: -5888.040235953891
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1374  total reward: -5893.033901466016
  Simulating cascading failure
  ok
timestep 1375  total reward: -5898.4348352289635
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1376  total reward: -5912.4348352289635
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1377  total reward: -5926.4348352289635
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1378  total reward: -5940.4348352289635
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1379  total reward: -5946.002693756807
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1380  total reward: -5960.002693756807
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1381  total reward: -5974.002693756807
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1382  total reward: -5978.799821737846
  Simulating cascading failure
  ok
timestep 1383  total reward: -5982.693224943923
  Simulating cascading failure
  ok
timestep 1384  total reward: -5985.847859293518
  Simulating cascading failure
  ok
timestep 1385  total reward: -5988.495436687661
  Simulating cascading failure
  ok
timestep 1386  total reward: -5990.847538273279
  Simulating cascading failure
  ok
timestep 1387  total reward: -5993.391871350301
  Simulating cascading failure
  ok
timestep 1388  total reward: -5996.647572033497
  Simulating cascading failure
  ok
timestep 1389  total reward: -6000.837545819685
  Simulating cascading failure
  ok
timestep 1390  total reward: -6006.060936547915
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1391  total reward: -6020.060936547915
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1392  total reward: -6034.060936547915
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1393  total reward: -6048.060936547915
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1394  total reward: -6054.317798830517
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1395  total reward: -6068.317798830517
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1396  total reward: -6082.317798830517
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1397  total reward: -6087.4815459072815
  Simulating cascading failure
  ok
timestep 1398  total reward: -6092.093848590813
  Simulating cascading failure
  ok
timestep 1399  total reward: -6096.955039239342
  Simulating cascading failure
  ok
timestep 1400  total reward: -6102.726606277358
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1401  total reward: -6116.726606277358
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1402  total reward: -6130.726606277358
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1403  total reward: -6144.726606277358
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1404  total reward: -6158.726606277358
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1405  total reward: -6164.526250477475
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1406  total reward: -6178.526250477475
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1407  total reward: -6179.886804649716
  Simulating cascading failure
  ok
timestep 1408  total reward: -6181.110693813199
  Simulating cascading failure
  ok
timestep 1409  total reward: -6182.01862588862
  Simulating cascading failure
  ok
timestep 1410  total reward: -6182.8628064348395
  Simulating cascading failure
  ok
timestep 1411  total reward: -6183.726664926596
  Simulating cascading failure
  ok
timestep 1412  total reward: -6184.696839895934
  Simulating cascading failure
  ok
timestep 1413  total reward: -6186.178837572171
  Simulating cascading failure
  ok
timestep 1414  total reward: -6188.03247813845
  Simulating cascading failure
  ok
timestep 1415  total reward: -6189.87107679056
  Simulating cascading failure
  ok
timestep 1416  total reward: -6191.716542457769
  Simulating cascading failure
  ok
timestep 1417  total reward: -6193.690323564119
  Simulating cascading failure
  ok
timestep 1418  total reward: -6195.772853303823
  Simulating cascading failure
  ok
timestep 1419  total reward: -6197.807263748327
  Simulating cascading failure
  ok
timestep 1420  total reward: -6199.767612427157
  Simulating cascading failure
  ok
timestep 1421  total reward: -6201.585370248417
  Simulating cascading failure
  ok
timestep 1422  total reward: -6203.217350836624
  Simulating cascading failure
  ok
timestep 1423  total reward: -6204.823722777385
  Simulating cascading failure
  ok
timestep 1424  total reward: -6206.489166656473
  Simulating cascading failure
  ok
timestep 1425  total reward: -6208.416588232059
  Simulating cascading failure
  ok
timestep 1426  total reward: -6210.3371684722315
  Simulating cascading failure
  ok
timestep 1427  total reward: -6211.970545197342
  Simulating cascading failure
  ok
timestep 1428  total reward: -6213.560500601081
  Simulating cascading failure
  ok
timestep 1429  total reward: -6214.7343502411895
  Simulating cascading failure
  ok
timestep 1430  total reward: -6215.754666373785
  Simulating cascading failure
  ok
timestep 1431  total reward: -6216.904399591844
  Simulating cascading failure
  ok
timestep 1432  total reward: -6217.810973696041
  Simulating cascading failure
  ok
timestep 1433  total reward: -6218.631828555968
  Simulating cascading failure
  ok
timestep 1434  total reward: -6219.413124487526
  Simulating cascading failure
  ok
timestep 1435  total reward: -6220.167959888779
  Simulating cascading failure
  ok
timestep 1436  total reward: -6221.133017147666
  Simulating cascading failure
  ok
timestep 1437  total reward: -6222.362672187121
  Simulating cascading failure
  ok
timestep 1438  total reward: -6223.822691808171
  Simulating cascading failure
  ok
timestep 1439  total reward: -6225.783113683201
  Simulating cascading failure
  ok
timestep 1440  total reward: -6227.833491322038
  Simulating cascading failure
  ok
timestep 1441  total reward: -6230.147988353958
  Simulating cascading failure
  ok
timestep 1442  total reward: -6232.516189432107
  Simulating cascading failure
  ok
timestep 1443  total reward: -6234.412871363008
  Simulating cascading failure
  ok
timestep 1444  total reward: -6236.6148512277605
  Simulating cascading failure
  ok
timestep 1445  total reward: -6238.63934485729
  Simulating cascading failure
  ok
timestep 1446  total reward: -6240.051930702196
  Simulating cascading failure
  ok
timestep 1447  total reward: -6241.654252284419
  Simulating cascading failure
  ok
timestep 1448  total reward: -6243.48160686426
  Simulating cascading failure
  ok
timestep 1449  total reward: -6245.293247065533
  Simulating cascading failure
  ok
timestep 1450  total reward: -6246.630629059823
  Simulating cascading failure
  ok
timestep 1451  total reward: -6247.801455691425
  Simulating cascading failure
  ok
timestep 1452  total reward: -6249.238497592995
  Simulating cascading failure
  ok
timestep 1453  total reward: -6250.625091301673
  Simulating cascading failure
  ok
timestep 1454  total reward: -6251.722312178388
  Simulating cascading failure
  ok
timestep 1455  total reward: -6252.425118912703
  Simulating cascading failure
  ok
timestep 1456  total reward: -6253.099206069867
  Simulating cascading failure
  ok
timestep 1457  total reward: -6253.6895461866525
  Simulating cascading failure
  ok
timestep 1458  total reward: -6254.198701324596
  Simulating cascading failure
  ok
timestep 1459  total reward: -6254.75333310159
  Simulating cascading failure
  ok
timestep 1460  total reward: -6255.410630848383
  Simulating cascading failure
  ok
timestep 1461  total reward: -6256.427552420603
  Simulating cascading failure
  ok
timestep 1462  total reward: -6257.775855243069
  Simulating cascading failure
  ok
timestep 1463  total reward: -6259.20356121675
  Simulating cascading failure
  ok
timestep 1464  total reward: -6260.623071715789
  Simulating cascading failure
  ok
timestep 1465  total reward: -6261.930821799745
  Simulating cascading failure
  ok
timestep 1466  total reward: -6263.146127660732
  Simulating cascading failure
  ok
timestep 1467  total reward: -6264.416041797388
  Simulating cascading failure
  ok
timestep 1468  total reward: -6265.629974759732
  Simulating cascading failure
  ok
timestep 1469  total reward: -6266.713071584179
  Simulating cascading failure
  ok
timestep 1470  total reward: -6267.76977620836
  Simulating cascading failure
  ok
timestep 1471  total reward: -6268.76229151293
  Simulating cascading failure
  ok
timestep 1472  total reward: -6269.931974688637
  Simulating cascading failure
  ok
timestep 1473  total reward: -6271.275687287381
  Simulating cascading failure
  ok
timestep 1474  total reward: -6272.436276251987
  Simulating cascading failure
  ok
timestep 1475  total reward: -6273.411594214623
  Simulating cascading failure
  ok
timestep 1476  total reward: -6274.364086130324
  Simulating cascading failure
  ok
timestep 1477  total reward: -6275.343941360201
  Simulating cascading failure
  ok
timestep 1478  total reward: -6276.12043642717
  Simulating cascading failure
  ok
timestep 1479  total reward: -6276.669034858676
  Simulating cascading failure
  ok
timestep 1480  total reward: -6277.2335358372
  Simulating cascading failure
  ok
timestep 1481  total reward: -6277.733737634795
  Simulating cascading failure
  ok
timestep 1482  total reward: -6278.100990518123
  Simulating cascading failure
  ok
timestep 1483  total reward: -6278.5056715178225
  Simulating cascading failure
  ok
timestep 1484  total reward: -6279.019197238346
  Simulating cascading failure
  ok
timestep 1485  total reward: -6279.7215634968015
  Simulating cascading failure
  ok
timestep 1486  total reward: -6280.880808997819
  Simulating cascading failure
  ok
timestep 1487  total reward: -6282.069413428147
  Simulating cascading failure
  ok
timestep 1488  total reward: -6283.041474182995
  Simulating cascading failure
  ok
timestep 1489  total reward: -6284.081629985527
  Simulating cascading failure
  ok
timestep 1490  total reward: -6285.088435968619
  Simulating cascading failure
  ok
timestep 1491  total reward: -6286.115563177411
  Simulating cascading failure
  ok
timestep 1492  total reward: -6287.053037024538
  Simulating cascading failure
  ok
timestep 1493  total reward: -6287.837027699819
  Simulating cascading failure
  ok
timestep 1494  total reward: -6288.607797760202
  Simulating cascading failure
  ok
timestep 1495  total reward: -6289.387333089151
  Simulating cascading failure
  ok
timestep 1496  total reward: -6290.364074445497
  Simulating cascading failure
  ok
timestep 1497  total reward: -6291.50377057032
  Simulating cascading failure
  ok
timestep 1498  total reward: -6292.5437473096135
  Simulating cascading failure
  ok
timestep 1499  total reward: -6293.44400553669
  Simulating cascading failure
  ok
timestep 1500  total reward: -6294.405353153181
  Simulating cascading failure
  ok
timestep 1501  total reward: -6295.345011076975
  Simulating cascading failure
  ok
timestep 1502  total reward: -6296.517957389584
  Simulating cascading failure
  ok
timestep 1503  total reward: -6297.828599200309
  Simulating cascading failure
  ok
timestep 1504  total reward: -6298.764053075207
  Simulating cascading failure
  ok
timestep 1505  total reward: -6299.522767677738
  Simulating cascading failure
  ok
timestep 1506  total reward: -6300.198200788673
  Simulating cascading failure
  ok
timestep 1507  total reward: -6300.950534986807
  Simulating cascading failure
  ok
timestep 1508  total reward: -6301.855533010454
  Simulating cascading failure
  ok
timestep 1509  total reward: -6303.032866239387
  Simulating cascading failure
  ok
timestep 1510  total reward: -6304.571165990981
  Simulating cascading failure
  ok
timestep 1511  total reward: -6306.226562723892
  Simulating cascading failure
  ok
timestep 1512  total reward: -6307.939979419898
  Simulating cascading failure
  ok
timestep 1513  total reward: -6310.265583849726
  Simulating cascading failure
  ok
timestep 1514  total reward: -6312.551175634558
  Simulating cascading failure
  ok
timestep 1515  total reward: -6314.33608259782
  Simulating cascading failure
  ok
timestep 1516  total reward: -6316.117995241418
  Simulating cascading failure
  ok
timestep 1517  total reward: -6317.700559483638
  Simulating cascading failure
  ok
timestep 1518  total reward: -6319.082220931661
  Simulating cascading failure
  ok
timestep 1519  total reward: -6320.493001772877
  Simulating cascading failure
  ok
timestep 1520  total reward: -6322.3122515937475
  Simulating cascading failure
  ok
timestep 1521  total reward: -6324.671232388353
  Simulating cascading failure
  ok
timestep 1522  total reward: -6326.727816887684
  Simulating cascading failure
  ok
timestep 1523  total reward: -6328.175397036621
  Simulating cascading failure
  ok
timestep 1524  total reward: -6329.458132726115
  Simulating cascading failure
  ok
timestep 1525  total reward: -6330.968756764915
  Simulating cascading failure
  ok
timestep 1526  total reward: -6332.560844969432
  Simulating cascading failure
  ok
timestep 1527  total reward: -6333.797957527508
  Simulating cascading failure
  ok
timestep 1528  total reward: -6334.844168020891
  Simulating cascading failure
  ok
timestep 1529  total reward: -6335.698437162284
  Simulating cascading failure
  ok
timestep 1530  total reward: -6336.541400954735
  Simulating cascading failure
  ok
timestep 1531  total reward: -6337.258871749687
  Simulating cascading failure
  ok
timestep 1532  total reward: -6338.173053392713
  Simulating cascading failure
  ok
timestep 1533  total reward: -6339.679504688564
  Simulating cascading failure
  ok
timestep 1534  total reward: -6341.3437116242285
  Simulating cascading failure
  ok
timestep 1535  total reward: -6343.051400580904
  Simulating cascading failure
  ok
timestep 1536  total reward: -6345.323835967334
  Simulating cascading failure
  ok
timestep 1537  total reward: -6347.8374322386135
  Simulating cascading failure
  ok
timestep 1538  total reward: -6350.364466522402
  Simulating cascading failure
  ok
timestep 1539  total reward: -6352.694631079539
  Simulating cascading failure
  ok
timestep 1540  total reward: -6354.4241945212525
  Simulating cascading failure
  ok
timestep 1541  total reward: -6355.987446010471
  Simulating cascading failure
  ok
timestep 1542  total reward: -6357.430993353191
  Simulating cascading failure
  ok
timestep 1543  total reward: -6358.986496532114
  Simulating cascading failure
  ok
timestep 1544  total reward: -6360.86100593736
  Simulating cascading failure
  ok
timestep 1545  total reward: -6362.913181105629
  Simulating cascading failure
  ok
timestep 1546  total reward: -6365.048880015258
  Simulating cascading failure
  ok
timestep 1547  total reward: -6366.922635932835
  Simulating cascading failure
  ok
timestep 1548  total reward: -6368.5202042129795
  Simulating cascading failure
  ok
timestep 1549  total reward: -6370.09850712655
  Simulating cascading failure
  ok
timestep 1550  total reward: -6371.585448276008
  Simulating cascading failure
  ok
timestep 1551  total reward: -6372.874451079293
  Simulating cascading failure
  ok
timestep 1552  total reward: -6373.954436629598
  Simulating cascading failure
  ok
timestep 1553  total reward: -6374.859881842074
  Simulating cascading failure
  ok
timestep 1554  total reward: -6375.620147517331
  Simulating cascading failure
  ok
timestep 1555  total reward: -6376.525950264846
  Simulating cascading failure
  ok
timestep 1556  total reward: -6377.679278081292
  Simulating cascading failure
  ok
timestep 1557  total reward: -6379.028939483482
  Simulating cascading failure
  ok
timestep 1558  total reward: -6380.607061089262
  Simulating cascading failure
  ok
timestep 1559  total reward: -6382.44410955686
  Simulating cascading failure
  ok
timestep 1560  total reward: -6384.487719648266
  Simulating cascading failure
  ok
timestep 1561  total reward: -6386.577155703562
  Simulating cascading failure
  ok
timestep 1562  total reward: -6388.65163879021
  Simulating cascading failure
  ok
timestep 1563  total reward: -6390.814412047539
  Simulating cascading failure
  ok
timestep 1564  total reward: -6393.017170768286
  Simulating cascading failure
  ok
timestep 1565  total reward: -6394.84063809492
  Simulating cascading failure
  ok
timestep 1566  total reward: -6396.381821051211
  Simulating cascading failure
  ok
timestep 1567  total reward: -6397.940496395742
  Simulating cascading failure
  ok
timestep 1568  total reward: -6399.649523052515
  Simulating cascading failure
  ok
timestep 1569  total reward: -6401.701181767614
  Simulating cascading failure
  ok
timestep 1570  total reward: -6403.656260349888
  Simulating cascading failure
  ok
timestep 1571  total reward: -6405.321920250433
  Simulating cascading failure
  ok
timestep 1572  total reward: -6406.950884248461
  Simulating cascading failure
  ok
timestep 1573  total reward: -6408.521978814231
  Simulating cascading failure
  ok
timestep 1574  total reward: -6409.915940291758
  Simulating cascading failure
  ok
timestep 1575  total reward: -6411.107181833715
  Simulating cascading failure
  ok
timestep 1576  total reward: -6412.12769382197
  Simulating cascading failure
  ok
timestep 1577  total reward: -6413.079088468478
  Simulating cascading failure
  ok
timestep 1578  total reward: -6414.026434627477
  Simulating cascading failure
  ok
timestep 1579  total reward: -6415.016922491349
  Simulating cascading failure
  ok
timestep 1580  total reward: -6416.155140491472
  Simulating cascading failure
  ok
timestep 1581  total reward: -6417.751944077781
  Simulating cascading failure
  ok
timestep 1582  total reward: -6419.646263988482
  Simulating cascading failure
  ok
timestep 1583  total reward: -6421.637106394725
  Simulating cascading failure
  ok
timestep 1584  total reward: -6423.663166680223
  Simulating cascading failure
  ok
timestep 1585  total reward: -6426.1322398755165
  Simulating cascading failure
  ok
timestep 1586  total reward: -6428.679868017683
  Simulating cascading failure
  ok
timestep 1587  total reward: -6431.034680846289
  Simulating cascading failure
  ok
timestep 1588  total reward: -6433.314488552969
  Simulating cascading failure
  ok
timestep 1589  total reward: -6435.116300565452
  Simulating cascading failure
  ok
timestep 1590  total reward: -6436.71971384336
  Simulating cascading failure
  ok
timestep 1591  total reward: -6439.121076337801
  Simulating cascading failure
  ok
timestep 1592  total reward: -6441.845131778435
  Simulating cascading failure
  ok
timestep 1593  total reward: -6443.337258450188
  Simulating cascading failure
  ok
timestep 1594  total reward: -6444.683542367109
  Simulating cascading failure
  ok
timestep 1595  total reward: -6446.29730275208
  Simulating cascading failure
  ok
timestep 1596  total reward: -6447.863761824774
  Simulating cascading failure
  ok
timestep 1597  total reward: -6449.507413937998
  Simulating cascading failure
  ok
timestep 1598  total reward: -6450.892559772576
  Simulating cascading failure
  ok
timestep 1599  total reward: -6452.241658003102
  Simulating cascading failure
  ok
timestep 1600  total reward: -6453.411016882101
  Simulating cascading failure
  ok
timestep 1601  total reward: -6454.238660827394
  Simulating cascading failure
  ok
timestep 1602  total reward: -6455.037526141138
  Simulating cascading failure
  ok
timestep 1603  total reward: -6455.861513971193
  Simulating cascading failure
  ok
timestep 1604  total reward: -6456.617510349606
  Simulating cascading failure
  ok
timestep 1605  total reward: -6457.713613580465
  Simulating cascading failure
  ok
timestep 1606  total reward: -6459.334784696348
  Simulating cascading failure
  ok
timestep 1607  total reward: -6461.294102158256
  Simulating cascading failure
  ok
timestep 1608  total reward: -6463.338100313169
  Simulating cascading failure
  ok
timestep 1609  total reward: -6465.440114285901
  Simulating cascading failure
  ok
timestep 1610  total reward: -6467.624772493239
  Simulating cascading failure
  ok
timestep 1611  total reward: -6469.5760945638485
  Simulating cascading failure
  ok
timestep 1612  total reward: -6471.259479328914
  Simulating cascading failure
  ok
timestep 1613  total reward: -6472.805302382723
  Simulating cascading failure
  ok
timestep 1614  total reward: -6474.3390013494245
  Simulating cascading failure
  ok
timestep 1615  total reward: -6475.860574963715
  Simulating cascading failure
  ok
timestep 1616  total reward: -6477.784322467077
  Simulating cascading failure
  ok
timestep 1617  total reward: -6479.825054184561
  Simulating cascading failure
  ok
timestep 1618  total reward: -6481.517984420469
  Simulating cascading failure
  ok
timestep 1619  total reward: -6482.964114927186
  Simulating cascading failure
  ok
timestep 1620  total reward: -6484.3702098997055
  Simulating cascading failure
  ok
timestep 1621  total reward: -6485.829325258848
  Simulating cascading failure
  ok
timestep 1622  total reward: -6486.973963491729
  Simulating cascading failure
  ok
timestep 1623  total reward: -6487.722521387548
  Simulating cascading failure
  ok
timestep 1624  total reward: -6488.326950697503
  Simulating cascading failure
  ok
timestep 1625  total reward: -6488.891891757869
  Simulating cascading failure
  ok
timestep 1626  total reward: -6489.447206634442
  Simulating cascading failure
  ok
timestep 1627  total reward: -6490.115073536764
  Simulating cascading failure
  ok
timestep 1628  total reward: -6490.822879811888
  Simulating cascading failure
  ok
timestep 1629  total reward: -6491.756809710391
  Simulating cascading failure
  ok
timestep 1630  total reward: -6492.969867398238
  Simulating cascading failure
  ok
timestep 1631  total reward: -6494.170067341303
  Simulating cascading failure
  ok
timestep 1632  total reward: -6495.492156705591
  Simulating cascading failure
  ok
timestep 1633  total reward: -6497.2016408705385
  Simulating cascading failure
  ok
timestep 1634  total reward: -6498.911115711318
  Simulating cascading failure
  ok
timestep 1635  total reward: -6500.238380286337
  Simulating cascading failure
  ok
timestep 1636  total reward: -6501.366853344167
  Simulating cascading failure
  ok
timestep 1637  total reward: -6502.424478403179
  Simulating cascading failure
  ok
timestep 1638  total reward: -6503.365734363382
  Simulating cascading failure
  ok
timestep 1639  total reward: -6504.345259488677
  Simulating cascading failure
  ok
timestep 1640  total reward: -6505.4619906923
  Simulating cascading failure
  ok
timestep 1641  total reward: -6506.641907503101
  Simulating cascading failure
  ok
timestep 1642  total reward: -6507.823158849736
  Simulating cascading failure
  ok
timestep 1643  total reward: -6508.817181033314
  Simulating cascading failure
  ok
timestep 1644  total reward: -6509.947381745675
  Simulating cascading failure
  ok
timestep 1645  total reward: -6511.098962150095
  Simulating cascading failure
  ok
timestep 1646  total reward: -6511.9271152860465
  Simulating cascading failure
  ok
timestep 1647  total reward: -6512.638464458523
  Simulating cascading failure
  ok
timestep 1648  total reward: -6513.320184352338
  Simulating cascading failure
  ok
timestep 1649  total reward: -6513.859978531273
  Simulating cascading failure
  ok
timestep 1650  total reward: -6514.25856384726
  Simulating cascading failure
  ok
timestep 1651  total reward: -6514.660588189339
  Simulating cascading failure
  ok
timestep 1652  total reward: -6515.319607267385
  Simulating cascading failure
  ok
timestep 1653  total reward: -6515.933621149836
  Simulating cascading failure
  ok
timestep 1654  total reward: -6516.713725546658
  Simulating cascading failure
  ok
timestep 1655  total reward: -6517.84651142732
  Simulating cascading failure
  ok
timestep 1656  total reward: -6518.870265631194
  Simulating cascading failure
  ok
timestep 1657  total reward: -6519.907830054703
  Simulating cascading failure
  ok
timestep 1658  total reward: -6520.9579063214505
  Simulating cascading failure
  ok
timestep 1659  total reward: -6521.979648437711
  Simulating cascading failure
  ok
timestep 1660  total reward: -6523.023199930381
  Simulating cascading failure
  ok
timestep 1661  total reward: -6523.95033426425
  Simulating cascading failure
  ok
timestep 1662  total reward: -6524.69653528966
  Simulating cascading failure
  ok
timestep 1663  total reward: -6525.460412443268
  Simulating cascading failure
  ok
timestep 1664  total reward: -6526.323400108344
  Simulating cascading failure
  ok
timestep 1665  total reward: -6527.396507407675
  Simulating cascading failure
  ok
timestep 1666  total reward: -6528.475312858556
  Simulating cascading failure
  ok
timestep 1667  total reward: -6529.338248564042
  Simulating cascading failure
  ok
timestep 1668  total reward: -6530.185990228254
  Simulating cascading failure
  ok
timestep 1669  total reward: -6531.079778436877
  Simulating cascading failure
  ok
timestep 1670  total reward: -6532.300930058075
  Simulating cascading failure
  ok
timestep 1671  total reward: -6533.532025259328
  Simulating cascading failure
  ok
timestep 1672  total reward: -6534.428367562917
  Simulating cascading failure
  ok
timestep 1673  total reward: -6535.245054341278
  Simulating cascading failure
  ok
timestep 1674  total reward: -6535.941262917544
  Simulating cascading failure
  ok
timestep 1675  total reward: -6536.624112061091
  Simulating cascading failure
  ok
timestep 1676  total reward: -6537.605570178108
  Simulating cascading failure
  ok
timestep 1677  total reward: -6538.9951267802535
  Simulating cascading failure
  ok
timestep 1678  total reward: -6540.777434281576
  Simulating cascading failure
  ok
timestep 1679  total reward: -6542.690273041162
  Simulating cascading failure
  ok
timestep 1680  total reward: -6544.496561838991
  Simulating cascading failure
  ok
timestep 1681  total reward: -6546.575701808635
  Simulating cascading failure
  ok
timestep 1682  total reward: -6548.238748123705
  Simulating cascading failure
  ok
timestep 1683  total reward: -6549.933308703745
  Simulating cascading failure
  ok
timestep 1684  total reward: -6551.8194342374245
  Simulating cascading failure
  ok
timestep 1685  total reward: -6553.279639765578
  Simulating cascading failure
  ok
timestep 1686  total reward: -6555.00002740489
  Simulating cascading failure
  ok
timestep 1687  total reward: -6556.633907342309
  Simulating cascading failure
  ok
timestep 1688  total reward: -6558.20849775621
  Simulating cascading failure
  ok
timestep 1689  total reward: -6560.251874247104
  Simulating cascading failure
  ok
timestep 1690  total reward: -6562.217415467183
  Simulating cascading failure
  ok
timestep 1691  total reward: -6563.674105344494
  Simulating cascading failure
  ok
timestep 1692  total reward: -6565.05728985365
  Simulating cascading failure
  ok
timestep 1693  total reward: -6566.587285359943
  Simulating cascading failure
  ok
timestep 1694  total reward: -6567.999969638105
  Simulating cascading failure
  ok
timestep 1695  total reward: -6569.4170051465935
  Simulating cascading failure
  ok
timestep 1696  total reward: -6570.762846338994
  Simulating cascading failure
  ok
timestep 1697  total reward: -6571.749787232582
  Simulating cascading failure
  ok
timestep 1698  total reward: -6572.667574287463
  Simulating cascading failure
  ok
timestep 1699  total reward: -6573.649194812437
  Simulating cascading failure
  ok
timestep 1700  total reward: -6574.671619368562
  Simulating cascading failure
  ok
timestep 1701  total reward: -6576.071619152386
  Simulating cascading failure
  ok
timestep 1702  total reward: -6577.9162630889
  Simulating cascading failure
  ok
timestep 1703  total reward: -6579.857986720421
  Simulating cascading failure
  ok
timestep 1704  total reward: -6581.945564839787
  Simulating cascading failure
  ok
timestep 1705  total reward: -6584.12185108244
  Simulating cascading failure
  ok
timestep 1706  total reward: -6586.274371738709
  Simulating cascading failure
  ok
timestep 1707  total reward: -6588.78017893803
  Simulating cascading failure
  ok
timestep 1708  total reward: -6590.681281058245
  Simulating cascading failure
  ok
timestep 1709  total reward: -6592.24215818712
  Simulating cascading failure
  ok
timestep 1710  total reward: -6594.2067988639465
  Simulating cascading failure
  ok
timestep 1711  total reward: -6595.823960363328
  Simulating cascading failure
  ok
timestep 1712  total reward: -6597.5993947533425
  Simulating cascading failure
  ok
timestep 1713  total reward: -6599.616922825734
  Simulating cascading failure
  ok
timestep 1714  total reward: -6601.80673563773
  Simulating cascading failure
  ok
timestep 1715  total reward: -6603.73465928099
  Simulating cascading failure
  ok
timestep 1716  total reward: -6605.194370998755
  Simulating cascading failure
  ok
timestep 1717  total reward: -6606.734034967513
  Simulating cascading failure
  ok
timestep 1718  total reward: -6608.205172678203
  Simulating cascading failure
  ok
timestep 1719  total reward: -6609.381416021821
  Simulating cascading failure
  ok
timestep 1720  total reward: -6610.331735592278
  Simulating cascading failure
  ok
timestep 1721  total reward: -6611.334646667362
  Simulating cascading failure
  ok
timestep 1722  total reward: -6612.391112153051
  Simulating cascading failure
  ok
timestep 1723  total reward: -6613.356111833524
  Simulating cascading failure
  ok
timestep 1724  total reward: -6614.471536229465
  Simulating cascading failure
  ok
timestep 1725  total reward: -6615.924317923722
  Simulating cascading failure
  ok
timestep 1726  total reward: -6617.56154752683
  Simulating cascading failure
  ok
timestep 1727  total reward: -6619.361540602071
  Simulating cascading failure
  ok
timestep 1728  total reward: -6621.298777111799
  Simulating cascading failure
  ok
timestep 1729  total reward: -6623.4293942159
  Simulating cascading failure
  ok
timestep 1730  total reward: -6625.682607687288
  Simulating cascading failure
  ok
timestep 1731  total reward: -6628.149920350644
  Simulating cascading failure
  ok
timestep 1732  total reward: -6630.607209781557
  Simulating cascading failure
  ok
timestep 1733  total reward: -6632.529822440138
  Simulating cascading failure
  ok
timestep 1734  total reward: -6634.15768796418
  Simulating cascading failure
  ok
timestep 1735  total reward: -6635.755705512718
  Simulating cascading failure
  ok
timestep 1736  total reward: -6637.60211246774
  Simulating cascading failure
  ok
timestep 1737  total reward: -6639.63903641811
  Simulating cascading failure
  ok
timestep 1738  total reward: -6641.401558303261
  Simulating cascading failure
  ok
timestep 1739  total reward: -6642.951791258627
  Simulating cascading failure
  ok
timestep 1740  total reward: -6644.622141738136
  Simulating cascading failure
  ok
timestep 1741  total reward: -6647.026252357371
  Simulating cascading failure
  ok
timestep 1742  total reward: -6649.238896957616
  Simulating cascading failure
  ok
timestep 1743  total reward: -6650.42454521528
  Simulating cascading failure
  ok
timestep 1744  total reward: -6651.336278876565
  Simulating cascading failure
  ok
timestep 1745  total reward: -6652.153917417751
  Simulating cascading failure
  ok
timestep 1746  total reward: -6652.911755163575
  Simulating cascading failure
  ok
timestep 1747  total reward: -6653.748503955934
  Simulating cascading failure
  ok
timestep 1748  total reward: -6654.730168084069
  Simulating cascading failure
  ok
timestep 1749  total reward: -6656.052421844717
  Simulating cascading failure
  ok
timestep 1750  total reward: -6657.8530344693445
  Simulating cascading failure
  ok
timestep 1751  total reward: -6659.8691733578
  Simulating cascading failure
  ok
timestep 1752  total reward: -6662.704948115488
  Simulating cascading failure
  ok
timestep 1753  total reward: -6665.491942094997
  Simulating cascading failure
  ok
timestep 1754  total reward: -6667.49561142126
  Simulating cascading failure
  ok
timestep 1755  total reward: -6669.095172893354
  Simulating cascading failure
  ok
timestep 1756  total reward: -6670.573180878751
  Simulating cascading failure
  ok
timestep 1757  total reward: -6672.263803414892
  Simulating cascading failure
  ok
timestep 1758  total reward: -6673.933877702003
  Simulating cascading failure
  ok
timestep 1759  total reward: -6675.7384574370935
  Simulating cascading failure
  ok
timestep 1760  total reward: -6677.575971437571
  Simulating cascading failure
  ok
timestep 1761  total reward: -6679.655086246574
  Simulating cascading failure
  ok
timestep 1762  total reward: -6681.626265090364
  Simulating cascading failure
  ok
timestep 1763  total reward: -6683.345916906551
  Simulating cascading failure
  ok
timestep 1764  total reward: -6685.114630296997
  Simulating cascading failure
  ok
timestep 1765  total reward: -6686.673646605276
  Simulating cascading failure
  ok
timestep 1766  total reward: -6688.129743187825
  Simulating cascading failure
  ok
timestep 1767  total reward: -6689.407495327749
  Simulating cascading failure
  ok
timestep 1768  total reward: -6690.381011148784
  Simulating cascading failure
  ok
timestep 1769  total reward: -6691.202689387817
  Simulating cascading failure
  ok
timestep 1770  total reward: -6691.928145245049
  Simulating cascading failure
  ok
timestep 1771  total reward: -6692.685769636886
  Simulating cascading failure
  ok
timestep 1772  total reward: -6693.664440475539
  Simulating cascading failure
  ok
timestep 1773  total reward: -6694.972483608615
  Simulating cascading failure
  ok
timestep 1774  total reward: -6696.503012253868
  Simulating cascading failure
  ok
timestep 1775  total reward: -6698.56570852669
  Simulating cascading failure
  ok
timestep 1776  total reward: -6700.668839013977
  Simulating cascading failure
  ok
timestep 1777  total reward: -6702.439212958662
  Simulating cascading failure
  ok
timestep 1778  total reward: -6704.3472709479865
  Simulating cascading failure
  ok
timestep 1779  total reward: -6706.290317430337
  Simulating cascading failure
  ok
timestep 1780  total reward: -6708.108943587136
  Simulating cascading failure
  ok
timestep 1781  total reward: -6709.6595294973795
  Simulating cascading failure
  ok
timestep 1782  total reward: -6711.083076423292
  Simulating cascading failure
  ok
timestep 1783  total reward: -6712.52962496156
  Simulating cascading failure
  ok
timestep 1784  total reward: -6714.469753824777
  Simulating cascading failure
  ok
timestep 1785  total reward: -6716.769834464539
  Simulating cascading failure
  ok
timestep 1786  total reward: -6718.627550890855
  Simulating cascading failure
  ok
timestep 1787  total reward: -6720.114256566079
  Simulating cascading failure
  ok
timestep 1788  total reward: -6721.236854639662
  Simulating cascading failure
  ok
timestep 1789  total reward: -6722.431654930811
  Simulating cascading failure
  ok
timestep 1790  total reward: -6723.736129246484
  Simulating cascading failure
  ok
timestep 1791  total reward: -6724.696038606953
  Simulating cascading failure
  ok
timestep 1792  total reward: -6725.422139930675
  Simulating cascading failure
  ok
timestep 1793  total reward: -6726.11419989185
  Simulating cascading failure
  ok
timestep 1794  total reward: -6726.755742749546
  Simulating cascading failure
  ok
timestep 1795  total reward: -6727.224973979091
  Simulating cascading failure
  ok
timestep 1796  total reward: -6727.810036759663
  Simulating cascading failure
  ok
timestep 1797  total reward: -6728.647046223626
  Simulating cascading failure
  ok
timestep 1798  total reward: -6729.699978715917
  Simulating cascading failure
  ok
timestep 1799  total reward: -6730.961284917932
  Simulating cascading failure
  ok
timestep 1800  total reward: -6732.29528697182
  Simulating cascading failure
  ok
timestep 1801  total reward: -6733.715899603386
  Simulating cascading failure
  ok
timestep 1802  total reward: -6735.1699580245095
  Simulating cascading failure
  ok
timestep 1803  total reward: -6736.406270955273
  Simulating cascading failure
  ok
timestep 1804  total reward: -6737.539016699113
  Simulating cascading failure
  ok
timestep 1805  total reward: -6738.610725408706
  Simulating cascading failure
  ok
timestep 1806  total reward: -6739.750182628438
  Simulating cascading failure
  ok
timestep 1807  total reward: -6740.907315887915
  Simulating cascading failure
  ok
timestep 1808  total reward: -6742.00996549087
  Simulating cascading failure
  ok
timestep 1809  total reward: -6743.237348007757
  Simulating cascading failure
  ok
timestep 1810  total reward: -6744.465111933414
  Simulating cascading failure
  ok
timestep 1811  total reward: -6745.572604380119
  Simulating cascading failure
  ok
timestep 1812  total reward: -6746.6861246959015
  Simulating cascading failure
  ok
timestep 1813  total reward: -6747.803644883034
  Simulating cascading failure
  ok
timestep 1814  total reward: -6748.680745239601
  Simulating cascading failure
  ok
timestep 1815  total reward: -6749.30767673909
  Simulating cascading failure
  ok
timestep 1816  total reward: -6749.808909823461
  Simulating cascading failure
  ok
timestep 1817  total reward: -6750.238225853125
  Simulating cascading failure
  ok
timestep 1818  total reward: -6750.656151824148
  Simulating cascading failure
  ok
timestep 1819  total reward: -6751.108456707302
  Simulating cascading failure
  ok
timestep 1820  total reward: -6751.700323482897
  Simulating cascading failure
  ok
timestep 1821  total reward: -6752.415790829917
  Simulating cascading failure
  ok
timestep 1822  total reward: -6753.285605384957
  Simulating cascading failure
  ok
timestep 1823  total reward: -6754.30106950705
  Simulating cascading failure
  ok
timestep 1824  total reward: -6755.374132086619
  Simulating cascading failure
  ok
timestep 1825  total reward: -6756.473695283636
  Simulating cascading failure
  ok
timestep 1826  total reward: -6757.774177223859
  Simulating cascading failure
  ok
timestep 1827  total reward: -6759.172363293723
  Simulating cascading failure
  ok
timestep 1828  total reward: -6760.398355175032
  Simulating cascading failure
  ok
timestep 1829  total reward: -6761.452847485441
  Simulating cascading failure
  ok
timestep 1830  total reward: -6762.307977101809
  Simulating cascading failure
  ok
timestep 1831  total reward: -6763.102874242204
  Simulating cascading failure
  ok
timestep 1832  total reward: -6764.102641319034
  Simulating cascading failure
  ok
timestep 1833  total reward: -6765.243170101165
  Simulating cascading failure
  ok
timestep 1834  total reward: -6766.134943690168
  Simulating cascading failure
  ok
timestep 1835  total reward: -6766.933706551079
  Simulating cascading failure
  ok
timestep 1836  total reward: -6767.786376494989
  Simulating cascading failure
  ok
timestep 1837  total reward: -6768.58105127459
  Simulating cascading failure
  ok
timestep 1838  total reward: -6769.496054171292
  Simulating cascading failure
  ok
timestep 1839  total reward: -6770.719373483413
  Simulating cascading failure
  ok
timestep 1840  total reward: -6771.824336621121
  Simulating cascading failure
  ok
timestep 1841  total reward: -6772.393819567238
  Simulating cascading failure
  ok
timestep 1842  total reward: -6772.912151730173
  Simulating cascading failure
  ok
timestep 1843  total reward: -6773.6195648248595
  Simulating cascading failure
  ok
timestep 1844  total reward: -6774.587992481664
  Simulating cascading failure
  ok
timestep 1845  total reward: -6775.920664809621
  Simulating cascading failure
  ok
timestep 1846  total reward: -6777.392205440869
  Simulating cascading failure
  ok
timestep 1847  total reward: -6779.296826445836
  Simulating cascading failure
  ok
timestep 1848  total reward: -6781.271663076477
  Simulating cascading failure
  ok
timestep 1849  total reward: -6783.014585512126
  Simulating cascading failure
  ok
timestep 1850  total reward: -6784.884037509664
  Simulating cascading failure
  ok
timestep 1851  total reward: -6786.736143992015
  Simulating cascading failure
  ok
timestep 1852  total reward: -6788.370159512184
  Simulating cascading failure
  ok
timestep 1853  total reward: -6789.839446166037
  Simulating cascading failure
  ok
timestep 1854  total reward: -6791.250302991282
  Simulating cascading failure
  ok
timestep 1855  total reward: -6792.639026136605
  Simulating cascading failure
  ok
timestep 1856  total reward: -6794.160618908307
  Simulating cascading failure
  ok
timestep 1857  total reward: -6795.783596261945
  Simulating cascading failure
  ok
timestep 1858  total reward: -6796.996069787907
  Simulating cascading failure
  ok
timestep 1859  total reward: -6798.0026263632135
  Simulating cascading failure
  ok
timestep 1860  total reward: -6799.396911055597
  Simulating cascading failure
  ok
timestep 1861  total reward: -6800.8900413686
  Simulating cascading failure
  ok
timestep 1862  total reward: -6802.345740768408
  Simulating cascading failure
  ok
timestep 1863  total reward: -6803.53352411127
  Simulating cascading failure
  ok
timestep 1864  total reward: -6804.440781349695
  Simulating cascading failure
  ok
timestep 1865  total reward: -6805.287167160219
  Simulating cascading failure
  ok
timestep 1866  total reward: -6806.087018568732
  Simulating cascading failure
  ok
timestep 1867  total reward: -6806.938052236135
  Simulating cascading failure
  ok
timestep 1868  total reward: -6807.962108483236
  Simulating cascading failure
  ok
timestep 1869  total reward: -6809.0003982940125
  Simulating cascading failure
  ok
timestep 1870  total reward: -6810.283105911127
  Simulating cascading failure
  ok
timestep 1871  total reward: -6812.5155423292745
  Simulating cascading failure
  ok
timestep 1872  total reward: -6814.958224768165
  Simulating cascading failure
  ok
timestep 1873  total reward: -6817.365759425091
  Simulating cascading failure
  ok
timestep 1874  total reward: -6819.804643774891
  Simulating cascading failure
  ok
timestep 1875  total reward: -6821.841012823031
  Simulating cascading failure
  ok
timestep 1876  total reward: -6823.7226535957825
  Simulating cascading failure
  ok
timestep 1877  total reward: -6825.365773434285
  Simulating cascading failure
  ok
timestep 1878  total reward: -6826.794479125275
  Simulating cascading failure
  ok
timestep 1879  total reward: -6828.237666658363
  Simulating cascading failure
  ok
timestep 1880  total reward: -6830.040887398579
  Simulating cascading failure
  ok
timestep 1881  total reward: -6832.401298109355
  Simulating cascading failure
  ok
timestep 1882  total reward: -6834.53521780504
  Simulating cascading failure
  ok
timestep 1883  total reward: -6836.222226705822
  Simulating cascading failure
  ok
timestep 1884  total reward: -6838.003354464817
  Simulating cascading failure
  ok
timestep 1885  total reward: -6839.964424042137
  Simulating cascading failure
  ok
timestep 1886  total reward: -6841.634436280108
  Simulating cascading failure
  ok
timestep 1887  total reward: -6842.81778730504
  Simulating cascading failure
  ok
timestep 1888  total reward: -6843.8343235891725
  Simulating cascading failure
  ok
timestep 1889  total reward: -6844.680164534077
  Simulating cascading failure
  ok
timestep 1890  total reward: -6845.429326979556
  Simulating cascading failure
  ok
timestep 1891  total reward: -6846.392716529899
  Simulating cascading failure
  ok
timestep 1892  total reward: -6847.508643629666
  Simulating cascading failure
  ok
timestep 1893  total reward: -6848.850084201034
  Simulating cascading failure
  ok
timestep 1894  total reward: -6850.857813037095
  Simulating cascading failure
  ok
timestep 1895  total reward: -6853.212215326388
  Simulating cascading failure
  ok
timestep 1896  total reward: -6855.360805864497
  Simulating cascading failure
  ok
timestep 1897  total reward: -6857.816526569859
  Simulating cascading failure
  ok
timestep 1898  total reward: -6860.291978895823
  Simulating cascading failure
  ok
timestep 1899  total reward: -6862.229623181115
  Simulating cascading failure
  ok
timestep 1900  total reward: -6864.056679300771
  Simulating cascading failure
  ok
timestep 1901  total reward: -6865.792695300552
  Simulating cascading failure
  ok
timestep 1902  total reward: -6867.544522476741
  Simulating cascading failure
  ok
timestep 1903  total reward: -6869.216993143048
  Simulating cascading failure
  ok
timestep 1904  total reward: -6871.658548633546
  Simulating cascading failure
  ok
timestep 1905  total reward: -6874.386824843585
  Simulating cascading failure
  ok
timestep 1906  total reward: -6876.194536215461
  Simulating cascading failure
  ok
timestep 1907  total reward: -6877.709263846538
  Simulating cascading failure
  ok
timestep 1908  total reward: -6878.921100381987
  Simulating cascading failure
  ok
timestep 1909  total reward: -6880.449383294248
  Simulating cascading failure
  ok
timestep 1910  total reward: -6882.256272513513
  Simulating cascading failure
  ok
timestep 1911  total reward: -6883.559789339796
  Simulating cascading failure
  ok
timestep 1912  total reward: -6884.563007145979
  Simulating cascading failure
  ok
timestep 1913  total reward: -6885.366967376321
  Simulating cascading failure
  ok
timestep 1914  total reward: -6886.37208073453
  Simulating cascading failure
  ok
timestep 1915  total reward: -6887.475698090473
  Simulating cascading failure
  ok
timestep 1916  total reward: -6888.531134836204
  Simulating cascading failure
  ok
timestep 1917  total reward: -6890.036560971289
  Simulating cascading failure
  ok
timestep 1918  total reward: -6891.912937301557
  Simulating cascading failure
  ok
timestep 1919  total reward: -6893.940111474212
  Simulating cascading failure
  ok
timestep 1920  total reward: -6896.433633394998
  Simulating cascading failure
  ok
timestep 1921  total reward: -6898.924851245359
  Simulating cascading failure
  ok
timestep 1922  total reward: -6901.090240731069
  Simulating cascading failure
  ok
timestep 1923  total reward: -6903.319396568093
  Simulating cascading failure
  ok
timestep 1924  total reward: -6905.647643893822
  Simulating cascading failure
  ok
timestep 1925  total reward: -6907.622758520734
  Simulating cascading failure
  ok
timestep 1926  total reward: -6909.191234887536
  Simulating cascading failure
  ok
timestep 1927  total reward: -6910.76891747324
  Simulating cascading failure
  ok
timestep 1928  total reward: -6912.422646432224
  Simulating cascading failure
  ok
timestep 1929  total reward: -6914.315113116991
  Simulating cascading failure
  ok
timestep 1930  total reward: -6916.117935341163
  Simulating cascading failure
  ok
timestep 1931  total reward: -6917.180331355153
  Simulating cascading failure
  ok
timestep 1932  total reward: -6918.33223165271
  Simulating cascading failure
  ok
timestep 1933  total reward: -6919.967375912519
  Simulating cascading failure
  ok
timestep 1934  total reward: -6921.434205049209
  Simulating cascading failure
  ok
timestep 1935  total reward: -6922.424286288897
  Simulating cascading failure
  ok
timestep 1936  total reward: -6923.114939031032
  Simulating cascading failure
  ok
timestep 1937  total reward: -6923.871150152458
  Simulating cascading failure
  ok
timestep 1938  total reward: -6924.579792487875
  Simulating cascading failure
  ok
timestep 1939  total reward: -6925.406549444908
  Simulating cascading failure
  ok
timestep 1940  total reward: -6926.4343598896485
  Simulating cascading failure
  ok
timestep 1941  total reward: -6927.368291011689
  Simulating cascading failure
  ok
timestep 1942  total reward: -6928.555664351349
  Simulating cascading failure
  ok
timestep 1943  total reward: -6930.26317991826
  Simulating cascading failure
  ok
timestep 1944  total reward: -6932.152661381751
  Simulating cascading failure
  ok
timestep 1945  total reward: -6934.128588360003
  Simulating cascading failure
  ok
timestep 1946  total reward: -6936.249065988806
  Simulating cascading failure
  ok
timestep 1947  total reward: -6938.246397967461
  Simulating cascading failure
  ok
timestep 1948  total reward: -6940.1074411878
  Simulating cascading failure
  ok
timestep 1949  total reward: -6941.911165846737
  Simulating cascading failure
  ok
timestep 1950  total reward: -6943.392478001606
  Simulating cascading failure
  ok
timestep 1951  total reward: -6944.823311458329
  Simulating cascading failure
  ok
timestep 1952  total reward: -6946.439171238166
  Simulating cascading failure
  ok
timestep 1953  total reward: -6948.330741983288
  Simulating cascading failure
  ok
timestep 1954  total reward: -6950.156512255984
  Simulating cascading failure
  ok
timestep 1955  total reward: -6951.558526697159
  Simulating cascading failure
  ok
timestep 1956  total reward: -6952.916231173951
  Simulating cascading failure
  ok
timestep 1957  total reward: -6954.563124181039
  Simulating cascading failure
  ok
timestep 1958  total reward: -6955.890254874374
  Simulating cascading failure
  ok
timestep 1959  total reward: -6956.715447871706
  Simulating cascading failure
  ok
timestep 1960  total reward: -6957.475092640752
  Simulating cascading failure
  ok
timestep 1961  total reward: -6958.099113051921
  Simulating cascading failure
  ok
timestep 1962  total reward: -6958.586231879235
  Simulating cascading failure
  ok
timestep 1963  total reward: -6959.12876633785
  Simulating cascading failure
  ok
timestep 1964  total reward: -6959.794838840064
  Simulating cascading failure
  ok
timestep 1965  total reward: -6960.805598675386
  Simulating cascading failure
  ok
timestep 1966  total reward: -6961.9884386283775
  Simulating cascading failure
  ok
timestep 1967  total reward: -6963.1749425705675
  Simulating cascading failure
  ok
timestep 1968  total reward: -6964.491122428017
  Simulating cascading failure
  ok
timestep 1969  total reward: -6966.11314435846
  Simulating cascading failure
  ok
timestep 1970  total reward: -6967.761687944333
  Simulating cascading failure
  ok
timestep 1971  total reward: -6969.139979557507
  Simulating cascading failure
  ok
timestep 1972  total reward: -6970.361184137756
  Simulating cascading failure
  ok
timestep 1973  total reward: -6971.324637129194
  Simulating cascading failure
  ok
timestep 1974  total reward: -6972.271280661158
  Simulating cascading failure
  ok
timestep 1975  total reward: -6973.333958775065
  Simulating cascading failure
  ok
timestep 1976  total reward: -6974.409617168443
  Simulating cascading failure
  ok
timestep 1977  total reward: -6975.5247514382845
  Simulating cascading failure
  ok
timestep 1978  total reward: -6976.7175846613245
  Simulating cascading failure
  ok
timestep 1979  total reward: -6977.808783628752
  Simulating cascading failure
  ok
timestep 1980  total reward: -6978.857346586527
  Simulating cascading failure
  ok
timestep 1981  total reward: -6979.872920870586
  Simulating cascading failure
  ok
timestep 1982  total reward: -6980.717113527887
  Simulating cascading failure
  ok
timestep 1983  total reward: -6981.396837194714
  Simulating cascading failure
  ok
timestep 1984  total reward: -6981.885744851315
  Simulating cascading failure
  ok
timestep 1985  total reward: -6982.285372911607
  Simulating cascading failure
  ok
timestep 1986  total reward: -6982.659026684378
  Simulating cascading failure
  ok
timestep 1987  total reward: -6983.02397260746
  Simulating cascading failure
  ok
timestep 1988  total reward: -6983.575012943324
  Simulating cascading failure
  ok
timestep 1989  total reward: -6984.329650453135
  Simulating cascading failure
  ok
timestep 1990  total reward: -6985.133453756261
  Simulating cascading failure
  ok
timestep 1991  total reward: -6986.062651863023
  Simulating cascading failure
  ok
timestep 1992  total reward: -6987.157571765549
  Simulating cascading failure
  ok
timestep 1993  total reward: -6988.232179568511
  Simulating cascading failure
  ok
timestep 1994  total reward: -6989.293800896488
  Simulating cascading failure
  ok
timestep 1995  total reward: -6990.7968135995
  Simulating cascading failure
  ok
timestep 1996  total reward: -6992.160064109124
  Simulating cascading failure
  ok
timestep 1997  total reward: -6992.947475833995
  Simulating cascading failure
  ok
timestep 1998  total reward: -6993.65742717109
  Simulating cascading failure
  ok
timestep 1999  total reward: -6994.3902199935455
  Simulating cascading failure
  ok
timestep 2000  total reward: -6995.230159089559
In [37]:
rewards_random_switchoff = run_policy(random_switch_off_policy)
Using chronics folder /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/chronics/14 and reference grid /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/reference_grid14.m
timestep 0001  total reward: -14
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0002  total reward: -16.858609831495585
  Simulating cascading failure
  ok
timestep 0003  total reward: -18.364603057032422
  Simulating cascading failure
  ok
timestep 0004  total reward: -20.061034580751656
  Simulating cascading failure
  ok
timestep 0005  total reward: -21.88209359307938
  Simulating cascading failure
  ok
timestep 0006  total reward: -24.02606892522541
timestep 0007  total reward: -38.02606892522541
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0008  total reward: -41.560375980216534
timestep 0009  total reward: -55.560375980216534
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0010  total reward: -58.86478229942441
timestep 0011  total reward: -72.8647822994244
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0012  total reward: -76.16608402513663
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0013  total reward: -90.16608402513663
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0014  total reward: -93.92073592351213
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0015  total reward: -107.92073592351213
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0016  total reward: -110.64857983440936
  Simulating cascading failure
  ok
timestep 0017  total reward: -113.00131516868377
  Simulating cascading failure
  ok
timestep 0018  total reward: -116.04365187974726
  Simulating cascading failure
  ok
timestep 0019  total reward: -119.14634650280732
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0020  total reward: -133.14634650280732
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0021  total reward: -135.73687841834303
  Simulating cascading failure
  ok
timestep 0022  total reward: -138.52954167690825
  Simulating cascading failure
  ok
timestep 0023  total reward: -141.69282985885945
  Simulating cascading failure
  ok
timestep 0024  total reward: -144.77167369063068
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0025  total reward: -158.77167369063068
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0026  total reward: -160.45842535594505
  Simulating cascading failure
  ok
timestep 0027  total reward: -162.63152919591408
  Simulating cascading failure
  ok
timestep 0028  total reward: -164.61930347605482
  Simulating cascading failure
  ok
timestep 0029  total reward: -166.87447439348986
  Simulating cascading failure
  ok
timestep 0030  total reward: -169.41335278664684
timestep 0031  total reward: -183.41335278664684
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0032  total reward: -186.70645274944715
  Simulating cascading failure
  ok
timestep 0033  total reward: -191.83519801913945
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0034  total reward: -205.83519801913945
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0035  total reward: -211.40805750535313
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0036  total reward: -225.40805750535313
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0037  total reward: -229.3618096709811
  Simulating cascading failure
  ok
timestep 0038  total reward: -233.26450143855354
  Simulating cascading failure
  ok
timestep 0039  total reward: -237.0117842205739
  Simulating cascading failure
  ok
timestep 0040  total reward: -240.93829687254342
  Simulating cascading failure
  ok
timestep 0041  total reward: -245.6319187056036
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0042  total reward: -259.6319187056036
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0043  total reward: -264.4479097829038
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0044  total reward: -278.4479097829038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0045  total reward: -281.54104211254736
timestep 0046  total reward: -295.54104211254736
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0047  total reward: -298.45162838722973
  Simulating cascading failure
  ok
timestep 0048  total reward: -300.74780858414596
  Simulating cascading failure
  ok
timestep 0049  total reward: -303.02984884779954
timestep 0050  total reward: -317.02984884779954
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0051  total reward: -318.6399069378784
  Simulating cascading failure
  ok
timestep 0052  total reward: -320.39639206501715
timestep 0053  total reward: -334.39639206501715
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0054  total reward: -336.90931057473534
timestep 0055  total reward: -350.90931057473534
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0056  total reward: -354.27430387179123
  Simulating cascading failure
  ok
timestep 0057  total reward: -358.30478199766554
timestep 0058  total reward: -372.30478199766554
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0059  total reward: -376.3640103139244
  Simulating cascading failure
  ok
timestep 0060  total reward: -380.47746928108484
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0061  total reward: -394.47746928108484
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0062  total reward: -408.47746928108484
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0063  total reward: -411.72813327524875
  Simulating cascading failure
  ok
timestep 0064  total reward: -414.88005718365946
  Simulating cascading failure
  ok
timestep 0065  total reward: -417.92302610291466
  Simulating cascading failure
  ok
timestep 0066  total reward: -421.99597064686867
  Simulating cascading failure
  ok
timestep 0067  total reward: -426.07492931241285
  Simulating cascading failure
  ok
timestep 0068  total reward: -429.63827476546095
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0069  total reward: -443.63827476546095
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0070  total reward: -446.5785640834707
  Simulating cascading failure
  ok
timestep 0071  total reward: -449.83707610713356
  Simulating cascading failure
  ok
timestep 0072  total reward: -452.9337414982782
timestep 0073  total reward: -466.9337414982782
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0074  total reward: -468.7407904810372
  Simulating cascading failure
  ok
timestep 0075  total reward: -470.8135241363178
  Simulating cascading failure
  ok
timestep 0076  total reward: -472.3625360031775
  Simulating cascading failure
  ok
timestep 0077  total reward: -473.95743581553853
  Simulating cascading failure
  ok
timestep 0078  total reward: -475.80318244440576
  Simulating cascading failure
  ok
timestep 0079  total reward: -481.0712695182874
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0080  total reward: -495.07126951828735
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0081  total reward: -498.8615317425361
  Simulating cascading failure
  ok
timestep 0082  total reward: -503.2900689259014
  Simulating cascading failure
  ok
timestep 0083  total reward: -507.2846146002466
  Simulating cascading failure
  ok
timestep 0084  total reward: -511.7354019125572
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0085  total reward: -525.7354019125572
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0086  total reward: -529.4899326243059
  Simulating cascading failure
  ok
timestep 0087  total reward: -533.199914032528
  Simulating cascading failure
  ok
timestep 0088  total reward: -537.1186233614217
  Simulating cascading failure
  ok
timestep 0089  total reward: -540.9910166016323
  Simulating cascading failure
  ok
timestep 0090  total reward: -545.0889246144383
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0091  total reward: -559.0889246144383
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0092  total reward: -562.9134429396877
  Simulating cascading failure
  ok
timestep 0093  total reward: -566.3349090774472
  Simulating cascading failure
  ok
timestep 0094  total reward: -569.755662197976
timestep 0095  total reward: -583.755662197976
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0096  total reward: -586.7107572703608
  Simulating cascading failure
  ok
timestep 0097  total reward: -588.2299446769047
  Simulating cascading failure
  ok
timestep 0098  total reward: -589.5934770322837
  Simulating cascading failure
  ok
timestep 0099  total reward: -591.426856622094
timestep 0100  total reward: -605.426856622094
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0101  total reward: -606.8926280749548
  Simulating cascading failure
  ok
timestep 0102  total reward: -608.6532761917671
  Simulating cascading failure
  ok
timestep 0103  total reward: -610.5915895507816
timestep 0104  total reward: -624.5915895507817
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0105  total reward: -628.6724397993681
  Simulating cascading failure
  ok
timestep 0106  total reward: -632.5347451538189
  Simulating cascading failure
  ok
timestep 0107  total reward: -637.1685386569769
timestep 0108  total reward: -651.1685386569769
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0109  total reward: -654.4807686838976
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0110  total reward: -668.4807686838976
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0111  total reward: -671.6919501836289
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0112  total reward: -685.6919501836289
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0113  total reward: -688.1211282785226
  Simulating cascading failure
  ok
timestep 0114  total reward: -690.916533582799
  Simulating cascading failure
  ok
timestep 0115  total reward: -694.1725558241278
  Simulating cascading failure
  ok
timestep 0116  total reward: -697.7652092690613
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0117  total reward: -711.7652092690613
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0118  total reward: -714.5570046425407
  Simulating cascading failure
  ok
timestep 0119  total reward: -717.7846491422938
  Simulating cascading failure
  ok
timestep 0120  total reward: -720.2841111270147
  Simulating cascading failure
  ok
timestep 0121  total reward: -722.007182935131
  Simulating cascading failure
  ok
timestep 0122  total reward: -723.3964808375656
  Simulating cascading failure
  ok
timestep 0123  total reward: -725.0625345814607
  Simulating cascading failure
  ok
timestep 0124  total reward: -726.1127352840386
timestep 0125  total reward: -740.1127352840386
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0126  total reward: -741.2384217228565
  Simulating cascading failure
  ok
timestep 0127  total reward: -743.09547448111
  Simulating cascading failure
  ok
timestep 0128  total reward: -745.489636702317
  Simulating cascading failure
  ok
timestep 0129  total reward: -749.3185936607051
  Simulating cascading failure
  ok
timestep 0130  total reward: -753.285060411971
timestep 0131  total reward: -767.285060411971
Game over! info: The grid is not connexe
timestep 0132  total reward: -781.285060411971
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0133  total reward: -783.8564821748225
  Simulating cascading failure
  ok
timestep 0134  total reward: -786.7360449452813
  Simulating cascading failure
  ok
timestep 0135  total reward: -789.1183827187057
  Simulating cascading failure
  ok
timestep 0136  total reward: -792.216236409932
  Simulating cascading failure
  ok
timestep 0137  total reward: -796.0396247671865
  Simulating cascading failure
  ok
timestep 0138  total reward: -799.8515114530529
  Simulating cascading failure
  ok
timestep 0139  total reward: -805.3973367904455
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0140  total reward: -819.3973367904455
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0141  total reward: -821.1343033607848
  Simulating cascading failure
  ok
timestep 0142  total reward: -823.0254347907678
timestep 0143  total reward: -837.0254347907678
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0144  total reward: -838.3293580558784
timestep 0145  total reward: -852.3293580558784
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0146  total reward: -853.1973995479873
  Simulating cascading failure
  ok
timestep 0147  total reward: -853.9751401433214
  Simulating cascading failure
  ok
timestep 0148  total reward: -854.5931659032078
  Simulating cascading failure
  ok
timestep 0149  total reward: -855.7539764243799
  Simulating cascading failure
  ok
timestep 0150  total reward: -857.0745350208383
  Simulating cascading failure
  ok
timestep 0151  total reward: -859.0109927811661
  Simulating cascading failure
  ok
timestep 0152  total reward: -861.1417244311218
  Simulating cascading failure
  ok
timestep 0153  total reward: -863.3446956623859
  Simulating cascading failure
  ok
timestep 0154  total reward: -865.5438926503366
  Simulating cascading failure
  ok
timestep 0155  total reward: -868.9821578640954
timestep 0156  total reward: -882.9821578640954
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0157  total reward: -884.8762376561963
timestep 0158  total reward: -898.8762376561963
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0159  total reward: -900.635951142011
  Simulating cascading failure
  ok
timestep 0160  total reward: -902.0565258761756
timestep 0161  total reward: -916.0565258761756
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0162  total reward: -917.7739768581872
  Simulating cascading failure
  ok
timestep 0163  total reward: -919.7099605996451
  Simulating cascading failure
  ok
timestep 0164  total reward: -921.6235757064044
  Simulating cascading failure
  ok
timestep 0165  total reward: -923.66406760482
  Simulating cascading failure
  ok
timestep 0166  total reward: -925.653200909113
  Simulating cascading failure
  ok
timestep 0167  total reward: -927.4325700537502
timestep 0168  total reward: -941.4325700537499
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0169  total reward: -943.2979095810742
  Simulating cascading failure
  ok
timestep 0170  total reward: -944.9530990037313
  Simulating cascading failure
  ok
timestep 0171  total reward: -946.7166456261402
timestep 0172  total reward: -960.7166456261402
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0173  total reward: -962.1880815119116
  Simulating cascading failure
  ok
timestep 0174  total reward: -964.0963230872001
  Simulating cascading failure
  ok
timestep 0175  total reward: -966.3028804507146
  Simulating cascading failure
  ok
timestep 0176  total reward: -968.9016718830338
  Simulating cascading failure
  ok
timestep 0177  total reward: -971.7372451672852
  Simulating cascading failure
  ok
timestep 0178  total reward: -974.6753521622542
  Simulating cascading failure
  ok
timestep 0179  total reward: -977.929897450776
  Simulating cascading failure
  ok
timestep 0180  total reward: -981.37187286638
  Simulating cascading failure
  ok
timestep 0181  total reward: -984.5121599459123
  Simulating cascading failure
  ok
timestep 0182  total reward: -989.1572672599789
timestep 0183  total reward: -1003.1572672599789
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0184  total reward: -1005.8017964894742
  Simulating cascading failure
  ok
timestep 0185  total reward: -1009.3818903187332
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0186  total reward: -1023.3818903187332
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0187  total reward: -1027.5773839352032
  Simulating cascading failure
  ok
timestep 0188  total reward: -1030.8065358731242
  Simulating cascading failure
  ok
timestep 0189  total reward: -1035.8367570106775
timestep 0190  total reward: -1049.8367570106775
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0191  total reward: -1051.5735799045842
  Simulating cascading failure
  ok
timestep 0192  total reward: -1054.2491402340843
  Simulating cascading failure
  ok
timestep 0193  total reward: -1056.696447620981
  Simulating cascading failure
  ok
timestep 0194  total reward: -1058.7178657528696
  Simulating cascading failure
  ok
timestep 0195  total reward: -1060.9373513188068
timestep 0196  total reward: -1074.9373513188068
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0197  total reward: -1076.2941509119223
  Simulating cascading failure
  ok
timestep 0198  total reward: -1078.1031556637074
  Simulating cascading failure
  ok
timestep 0199  total reward: -1081.5487755049708
timestep 0200  total reward: -1095.5487755049708
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0201  total reward: -1099.123193977041
  Simulating cascading failure
  ok
timestep 0202  total reward: -1103.1331544275886
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0203  total reward: -1117.1331544275886
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0204  total reward: -1122.554164353783
  Simulating cascading failure
  ok
timestep 0205  total reward: -1127.2644080814184
  Simulating cascading failure
  ok
timestep 0206  total reward: -1131.3965342864635
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0207  total reward: -1145.3965342864635
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0208  total reward: -1148.412744280677
  Simulating cascading failure
  ok
timestep 0209  total reward: -1151.8065015049112
  Simulating cascading failure
  ok
timestep 0210  total reward: -1156.8538324280457
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0211  total reward: -1170.8538324280457
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0212  total reward: -1174.3496083855664
  Simulating cascading failure
  ok
timestep 0213  total reward: -1177.554251653713
  Simulating cascading failure
  ok
timestep 0214  total reward: -1180.8542392828208
  Simulating cascading failure
  ok
timestep 0215  total reward: -1184.7332457395382
  Simulating cascading failure
  ok
timestep 0216  total reward: -1188.6745935688477
timestep 0217  total reward: -1202.6745935688477
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0218  total reward: -1204.4292072347864
  Simulating cascading failure
  ok
timestep 0219  total reward: -1205.8159125607144
  Simulating cascading failure
  ok
timestep 0220  total reward: -1207.5933271222316
  Simulating cascading failure
  ok
timestep 0221  total reward: -1209.451174088506
  Simulating cascading failure
  ok
timestep 0222  total reward: -1211.5406128210732
  Simulating cascading failure
  ok
timestep 0223  total reward: -1214.5342871545856
  Simulating cascading failure
  ok
timestep 0224  total reward: -1219.0551553633622
timestep 0225  total reward: -1233.0551553633622
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0226  total reward: -1236.742100757106
  Simulating cascading failure
  ok
timestep 0227  total reward: -1241.219012797368
  Simulating cascading failure
  ok
timestep 0228  total reward: -1245.2285665662198
  Simulating cascading failure
  ok
timestep 0229  total reward: -1249.6882528378878
timestep 0230  total reward: -1263.6882528378878
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0231  total reward: -1267.5317384151294
  Simulating cascading failure
  ok
timestep 0232  total reward: -1271.1584410720989
  Simulating cascading failure
  ok
timestep 0233  total reward: -1274.8898953941712
  Simulating cascading failure
  ok
timestep 0234  total reward: -1278.8043768304915
  Simulating cascading failure
  ok
timestep 0235  total reward: -1282.2396916995442
timestep 0236  total reward: -1296.2396916995442
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0237  total reward: -1299.2892977564738
  Simulating cascading failure
  ok
timestep 0238  total reward: -1302.2156390711903
  Simulating cascading failure
  ok
timestep 0239  total reward: -1305.0448578875107
  Simulating cascading failure
  ok
timestep 0240  total reward: -1307.5721018314423
  Simulating cascading failure
  ok
timestep 0241  total reward: -1309.9231835483192
  Simulating cascading failure
  ok
timestep 0242  total reward: -1311.8417446953533
  Simulating cascading failure
  ok
timestep 0243  total reward: -1315.0763773739832
  Simulating cascading failure
  ok
timestep 0244  total reward: -1318.2658128993287
timestep 0245  total reward: -1332.2658128993287
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0246  total reward: -1335.1710145550808
  Simulating cascading failure
  ok
timestep 0247  total reward: -1338.969946271814
  Simulating cascading failure
  ok
timestep 0248  total reward: -1343.29981204773
  Simulating cascading failure
  ok
timestep 0249  total reward: -1347.7988763842473
  Simulating cascading failure
  ok
timestep 0250  total reward: -1352.4897345242068
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
timestep 0251  total reward: -1366.4897345242068
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0252  total reward: -1370.5231608396803
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0253  total reward: -1384.5231608396803
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0254  total reward: -1398.5231608396803
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0255  total reward: -1401.6781719996843
timestep 0256  total reward: -1415.6781719996843
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0257  total reward: -1418.5726605974855
timestep 0258  total reward: -1432.5726605974855
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0259  total reward: -1435.6058000163762
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0260  total reward: -1449.6058000163762
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0261  total reward: -1452.507315475998
  Simulating cascading failure
  ok
timestep 0262  total reward: -1455.8747171726845
  Simulating cascading failure
  ok
timestep 0263  total reward: -1459.5459895477861
  Simulating cascading failure
  ok
timestep 0264  total reward: -1462.4252639901913
  Simulating cascading failure
  ok
timestep 0265  total reward: -1464.3470152535697
  Simulating cascading failure
  ok
timestep 0266  total reward: -1466.29005805728
  Simulating cascading failure
  ok
timestep 0267  total reward: -1468.3098127578028
  Simulating cascading failure
  ok
timestep 0268  total reward: -1470.1151593421446
  Simulating cascading failure
  ok
timestep 0269  total reward: -1472.4191992759206
  Simulating cascading failure
  ok
timestep 0270  total reward: -1475.5003494370603
timestep 0271  total reward: -1489.5003494370603
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0272  total reward: -1492.740796021
  Simulating cascading failure
  ok
timestep 0273  total reward: -1496.6499942763521
timestep 0274  total reward: -1510.6499942763521
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0275  total reward: -1524.6499942763521
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0276  total reward: -1528.575253689562
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0277  total reward: -1542.575253689562
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0278  total reward: -1545.7572565170408
  Simulating cascading failure
  ok
timestep 0279  total reward: -1548.7967192234778
  Simulating cascading failure
  ok
timestep 0280  total reward: -1551.735674515513
  Simulating cascading failure
  ok
timestep 0281  total reward: -1554.5912797862793
timestep 0282  total reward: -1568.5912797862793
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0283  total reward: -1572.8219568508741
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0284  total reward: -1586.8219568508741
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0285  total reward: -1589.8887985962356
  Simulating cascading failure
  ok
timestep 0286  total reward: -1592.805254257576
  Simulating cascading failure
  ok
timestep 0287  total reward: -1595.5299370071743
timestep 0288  total reward: -1609.5299370071746
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0289  total reward: -1610.9190021195993
  Simulating cascading failure
  ok
timestep 0290  total reward: -1612.6930865325166
  Simulating cascading failure
  ok
timestep 0291  total reward: -1613.759823481545
  Simulating cascading failure
  ok
timestep 0292  total reward: -1615.112144210934
  Simulating cascading failure
  ok
timestep 0293  total reward: -1617.0103835962445
timestep 0294  total reward: -1631.0103835962445
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0295  total reward: -1632.066302132262
  Simulating cascading failure
  ok
timestep 0296  total reward: -1633.8865185576688
  Simulating cascading failure
  ok
timestep 0297  total reward: -1636.5177627525832
timestep 0298  total reward: -1650.5177627525832
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0299  total reward: -1653.0048486381615
  Simulating cascading failure
  ok
timestep 0300  total reward: -1655.2749836156972
  Simulating cascading failure
  ok
timestep 0301  total reward: -1657.7386287697832
  Simulating cascading failure
  ok
timestep 0302  total reward: -1660.2258079240487
  Simulating cascading failure
  ok
timestep 0303  total reward: -1662.446056308866
timestep 0304  total reward: -1676.446056308866
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0305  total reward: -1678.670971143291
  Simulating cascading failure
  ok
timestep 0306  total reward: -1681.0156347891052
  Simulating cascading failure
  ok
timestep 0307  total reward: -1683.4997838827665
  Simulating cascading failure
  ok
timestep 0308  total reward: -1686.987640698048
  Simulating cascading failure
  ok
timestep 0309  total reward: -1690.8739795669958
timestep 0310  total reward: -1704.8739795669958
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0311  total reward: -1706.7137187025987
  Simulating cascading failure
  ok
timestep 0312  total reward: -1708.7936508263524
  Simulating cascading failure
  ok
timestep 0313  total reward: -1709.9183160518692
timestep 0314  total reward: -1723.9183160518692
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0315  total reward: -1724.7138195701673
  Simulating cascading failure
  ok
timestep 0316  total reward: -1725.4616393173678
  Simulating cascading failure
  ok
timestep 0317  total reward: -1726.6061399638324
timestep 0318  total reward: -1740.6061399638324
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0319  total reward: -1742.1474930603613
timestep 0320  total reward: -1756.147493060361
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0321  total reward: -1758.1588488902867
  Simulating cascading failure
  ok
timestep 0322  total reward: -1760.3068220790208
  Simulating cascading failure
  ok
timestep 0323  total reward: -1763.822190344689
  Simulating cascading failure
  ok
timestep 0324  total reward: -1767.2570855920983
  Simulating cascading failure
  ok
timestep 0325  total reward: -1770.567269318986
  Simulating cascading failure
  ok
timestep 0326  total reward: -1772.8333556361097
  Simulating cascading failure
  ok
timestep 0327  total reward: -1774.8763888277465
  Simulating cascading failure
  ok
timestep 0328  total reward: -1777.118231820582
  Simulating cascading failure
  ok
timestep 0329  total reward: -1779.7177998617826
  Simulating cascading failure
  ok
timestep 0330  total reward: -1783.7690158606554
  Simulating cascading failure
  ok
timestep 0331  total reward: -1788.2790992463538
timestep 0332  total reward: -1802.2790992463538
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0333  total reward: -1803.8193934981764
  Simulating cascading failure
  ok
timestep 0334  total reward: -1805.3631834828527
timestep 0335  total reward: -1819.3631834828527
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0336  total reward: -1821.2425984159847
  Simulating cascading failure
  ok
timestep 0337  total reward: -1824.5250633352343
  Simulating cascading failure
  ok
timestep 0338  total reward: -1827.8154487101415
timestep 0339  total reward: -1841.8154487101415
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0340  total reward: -1843.7404493544952
  Simulating cascading failure
  ok
timestep 0341  total reward: -1845.8418050010077
  Simulating cascading failure
  ok
timestep 0342  total reward: -1847.6122228825075
  Simulating cascading failure
  ok
timestep 0343  total reward: -1849.788957231504
  Simulating cascading failure
  ok
timestep 0344  total reward: -1852.8836148817809
timestep 0345  total reward: -1866.8836148817809
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0346  total reward: -1870.0740061176452
  Simulating cascading failure
  ok
timestep 0347  total reward: -1873.1880492770088
timestep 0348  total reward: -1887.1880492770088
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0349  total reward: -1890.479949018507
  Simulating cascading failure
  ok
timestep 0350  total reward: -1893.487492512802
  Simulating cascading failure
  ok
timestep 0351  total reward: -1896.2817522243975
  Simulating cascading failure
  ok
timestep 0352  total reward: -1899.893385544345
timestep 0353  total reward: -1913.893385544345
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0354  total reward: -1917.4831516512022
  Simulating cascading failure
  ok
timestep 0355  total reward: -1921.5629611037862
  Simulating cascading failure
  ok
timestep 0356  total reward: -1924.5918308704404
  Simulating cascading failure
  ok
timestep 0357  total reward: -1926.9816846985768
timestep 0358  total reward: -1940.9816846985768
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0359  total reward: -1943.245453093752
  Simulating cascading failure
  ok
timestep 0360  total reward: -1946.3101001344962
  Simulating cascading failure
  ok
timestep 0361  total reward: -1950.2123962332284
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0362  total reward: -1964.2123962332284
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0363  total reward: -1978.2123962332284
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0364  total reward: -1980.3817233858315
  Simulating cascading failure
  ok
timestep 0365  total reward: -1982.7430169872996
  Simulating cascading failure
  ok
timestep 0366  total reward: -1985.8144819296303
  Simulating cascading failure
  ok
timestep 0367  total reward: -1989.652544831185
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0368  total reward: -2003.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0369  total reward: -2017.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0370  total reward: -2031.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0371  total reward: -2045.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0372  total reward: -2059.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0373  total reward: -2073.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0374  total reward: -2087.652544831185
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0375  total reward: -2091.782719518355
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0376  total reward: -2105.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0377  total reward: -2119.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0378  total reward: -2133.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0379  total reward: -2147.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0380  total reward: -2161.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0381  total reward: -2175.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0382  total reward: -2189.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0383  total reward: -2203.782719518355
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0384  total reward: -2217.7827195183545
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0385  total reward: -2219.7499826527105
  Simulating cascading failure
  ok
timestep 0386  total reward: -2222.0266175336565
  Simulating cascading failure
  ok
timestep 0387  total reward: -2224.1630584381455
  Simulating cascading failure
  ok
timestep 0388  total reward: -2225.4410736301525
  Simulating cascading failure
  ok
timestep 0389  total reward: -2226.898367026947
timestep 0390  total reward: -2240.898367026947
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0391  total reward: -2243.3373301651673
  Simulating cascading failure
  ok
timestep 0392  total reward: -2246.435883921524
  Simulating cascading failure
  ok
timestep 0393  total reward: -2250.83750626707
  Simulating cascading failure
  ok
timestep 0394  total reward: -2255.485646535231
  Simulating cascading failure
  ok
timestep 0395  total reward: -2259.784396570699
timestep 0396  total reward: -2273.784396570699
Game over! info: The grid is not connexe
timestep 0397  total reward: -2287.784396570699
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0398  total reward: -2291.233665278998
  Simulating cascading failure
  ok
timestep 0399  total reward: -2294.3382205072485
timestep 0400  total reward: -2308.3382205072485
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0401  total reward: -2310.481865992935
  Simulating cascading failure
  ok
timestep 0402  total reward: -2313.244248103865
  Simulating cascading failure
  ok
timestep 0403  total reward: -2316.6646626798756
timestep 0404  total reward: -2330.6646626798756
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0405  total reward: -2334.6580468131215
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0406  total reward: -2348.6580468131215
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0407  total reward: -2362.6580468131215
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0408  total reward: -2364.7453356129063
  Simulating cascading failure
  ok
timestep 0409  total reward: -2367.7847294303047
timestep 0410  total reward: -2381.7847294303047
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0411  total reward: -2383.3423998977933
  Simulating cascading failure
  ok
timestep 0412  total reward: -2385.067538415328
  Simulating cascading failure
  ok
timestep 0413  total reward: -2386.6380457573437
  Simulating cascading failure
  ok
timestep 0414  total reward: -2388.4622358607508
timestep 0415  total reward: -2402.4622358607508
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0416  total reward: -2406.5466722359834
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0417  total reward: -2420.5466722359834
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0418  total reward: -2424.9977520424427
  Simulating cascading failure
  ok
timestep 0419  total reward: -2429.4558146965037
  Simulating cascading failure
  ok
timestep 0420  total reward: -2433.65486338101
  Simulating cascading failure
  ok
timestep 0421  total reward: -2438.0471730716195
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0422  total reward: -2452.0471730716195
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0423  total reward: -2456.2665076368817
  Simulating cascading failure
  ok
timestep 0424  total reward: -2460.3674012756496
  Simulating cascading failure
  ok
timestep 0425  total reward: -2464.7075857487516
timestep 0426  total reward: -2478.7075857487516
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0427  total reward: -2482.1983921741676
  Simulating cascading failure
  ok
timestep 0428  total reward: -2485.6353279558293
  Simulating cascading failure
  ok
timestep 0429  total reward: -2489.0265730608553
  Simulating cascading failure
  ok
timestep 0430  total reward: -2492.902486493407
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0431  total reward: -2506.902486493407
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0432  total reward: -2510.575559916552
  Simulating cascading failure
  ok
timestep 0433  total reward: -2512.8081326772704
  Simulating cascading failure
  ok
timestep 0434  total reward: -2514.645020428677
timestep 0435  total reward: -2528.645020428677
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0436  total reward: -2530.130230103977
  Simulating cascading failure
  ok
timestep 0437  total reward: -2531.416541003933
  Simulating cascading failure
  ok
timestep 0438  total reward: -2533.2188885040277
  Simulating cascading failure
  ok
timestep 0439  total reward: -2535.4479213797476
  Simulating cascading failure
  ok
timestep 0440  total reward: -2538.8297325764247
  Simulating cascading failure
  ok
timestep 0441  total reward: -2542.896252118399
  Simulating cascading failure
  ok
timestep 0442  total reward: -2546.712098664879
  Simulating cascading failure
  ok
timestep 0443  total reward: -2550.370803052152
  Simulating cascading failure
  ok
timestep 0444  total reward: -2554.3329782853593
  Simulating cascading failure
  ok
timestep 0445  total reward: -2558.518921750349
timestep 0446  total reward: -2572.518921750349
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0447  total reward: -2586.518921750349
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0448  total reward: -2589.11588865401
  Simulating cascading failure
  ok
timestep 0449  total reward: -2592.6296125814733
  Simulating cascading failure
  ok
timestep 0450  total reward: -2596.6856121570095
  Simulating cascading failure
  ok
timestep 0451  total reward: -2601.6632487335205
  Simulating cascading failure
  ok
timestep 0452  total reward: -2606.5694774060444
  Simulating cascading failure
  ok
timestep 0453  total reward: -2610.8834624932424
  Simulating cascading failure
  ok
timestep 0454  total reward: -2615.2075538347276
timestep 0455  total reward: -2629.2075538347276
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0456  total reward: -2631.6987923435586
timestep 0457  total reward: -2645.6987923435586
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0458  total reward: -2646.311025981157
  Simulating cascading failure
  ok
timestep 0459  total reward: -2647.016945539268
  Simulating cascading failure
  ok
timestep 0460  total reward: -2647.8860886209077
  Simulating cascading failure
  ok
timestep 0461  total reward: -2648.89001234196
  Simulating cascading failure
  ok
timestep 0462  total reward: -2650.2527924113706
  Simulating cascading failure
  ok
timestep 0463  total reward: -2651.7413894975916
  Simulating cascading failure
  ok
timestep 0464  total reward: -2653.6467579734854
  Simulating cascading failure
  ok
timestep 0465  total reward: -2656.9465849962703
  Simulating cascading failure
  ok
timestep 0466  total reward: -2660.9504533195454
  Simulating cascading failure
  ok
timestep 0467  total reward: -2665.9923704830862
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0468  total reward: -2679.9923704830862
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0469  total reward: -2684.006516782176
  Simulating cascading failure
  ok
timestep 0470  total reward: -2686.451539673061
  Simulating cascading failure
  ok
timestep 0471  total reward: -2688.5639557818704
  Simulating cascading failure
  ok
timestep 0472  total reward: -2690.430936816189
  Simulating cascading failure
  ok
timestep 0473  total reward: -2692.1270731573577
  Simulating cascading failure
  ok
timestep 0474  total reward: -2693.9104697744538
  Simulating cascading failure
  ok
timestep 0475  total reward: -2696.4634392843973
timestep 0476  total reward: -2710.4634392843973
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0477  total reward: -2712.1878565880497
  Simulating cascading failure
  ok
timestep 0478  total reward: -2713.8732619432185
  Simulating cascading failure
  ok
timestep 0479  total reward: -2715.717930762773
  Simulating cascading failure
  ok
timestep 0480  total reward: -2717.4727123023613
  Simulating cascading failure
  ok
timestep 0481  total reward: -2719.384329891718
timestep 0482  total reward: -2733.384329891718
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0483  total reward: -2734.159168449868
  Simulating cascading failure
  ok
timestep 0484  total reward: -2735.1261631267216
  Simulating cascading failure
  ok
timestep 0485  total reward: -2736.342568175877
  Simulating cascading failure
  ok
timestep 0486  total reward: -2738.112418872955
  Simulating cascading failure
  ok
timestep 0487  total reward: -2740.3687973299884
  Simulating cascading failure
  ok
timestep 0488  total reward: -2744.484518839289
  Simulating cascading failure
  ok
timestep 0489  total reward: -2748.789589712417
  Simulating cascading failure
  ok
timestep 0490  total reward: -2754.5756881096104
  Simulating cascading failure
  ok
timestep 0491  total reward: -2759.3957879010877
timestep 0492  total reward: -2773.3957879010877
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0493  total reward: -2776.0963162998232
  Simulating cascading failure
  ok
timestep 0494  total reward: -2778.627810015684
  Simulating cascading failure
  ok
timestep 0495  total reward: -2780.214506726801
  Simulating cascading failure
  ok
timestep 0496  total reward: -2781.7542258977983
  Simulating cascading failure
  ok
timestep 0497  total reward: -2783.439407500311
  Simulating cascading failure
  ok
timestep 0498  total reward: -2785.2626333178487
timestep 0499  total reward: -2799.2626333178487
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0500  total reward: -2801.07195777986
  Simulating cascading failure
  ok
timestep 0501  total reward: -2802.6232662822517
  Simulating cascading failure
  ok
timestep 0502  total reward: -2804.128864206189
  Simulating cascading failure
  ok
timestep 0503  total reward: -2805.8398756872384
  Simulating cascading failure
  ok
timestep 0504  total reward: -2809.325433668945
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0505  total reward: -2823.3254336689447
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0506  total reward: -2825.001740299438
  Simulating cascading failure
  ok
timestep 0507  total reward: -2826.616298639398
  Simulating cascading failure
  ok
timestep 0508  total reward: -2828.006506294146
timestep 0509  total reward: -2842.006506294146
Game over! info: The grid is not connexe
timestep 0510  total reward: -2856.006506294146
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0511  total reward: -2858.0870418123
  Simulating cascading failure
  ok
timestep 0512  total reward: -2860.924121780423
  Simulating cascading failure
  ok
timestep 0513  total reward: -2863.731571641285
  Simulating cascading failure
  ok
timestep 0514  total reward: -2865.90184730323
timestep 0515  total reward: -2879.90184730323
Game over! info: The grid is not connexe
timestep 0516  total reward: -2893.90184730323
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0517  total reward: -2897.6258066641603
  Simulating cascading failure
  ok
timestep 0518  total reward: -2900.6923530678814
  Simulating cascading failure
  ok
timestep 0519  total reward: -2902.9193808672358
  Simulating cascading failure
  ok
timestep 0520  total reward: -2905.3050298893754
  Simulating cascading failure
  ok
timestep 0521  total reward: -2908.8371072039563
  Simulating cascading failure
  ok
timestep 0522  total reward: -2912.7728464870715
  Simulating cascading failure
  ok
timestep 0523  total reward: -2916.9696843992424
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0524  total reward: -2930.9696843992424
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0525  total reward: -2933.5031962714497
  Simulating cascading failure
  ok
timestep 0526  total reward: -2936.3212768668736
  Simulating cascading failure
  ok
timestep 0527  total reward: -2939.0096256672787
  Simulating cascading failure
  ok
timestep 0528  total reward: -2941.6858591329237
  Simulating cascading failure
  ok
timestep 0529  total reward: -2944.333262947909
  Simulating cascading failure
  ok
timestep 0530  total reward: -2947.119926043647
  Simulating cascading failure
  ok
timestep 0531  total reward: -2949.6555242935847
  Simulating cascading failure
  ok
timestep 0532  total reward: -2951.4905780483923
  Simulating cascading failure
  ok
timestep 0533  total reward: -2954.5457616183194
  Simulating cascading failure
  ok
timestep 0534  total reward: -2958.3405592554327
timestep 0535  total reward: -2972.3405592554327
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0536  total reward: -2975.198281098839
  Simulating cascading failure
  ok
timestep 0537  total reward: -2978.0561699278805
  Simulating cascading failure
  ok
timestep 0538  total reward: -2982.1272604371215
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0539  total reward: -2996.1272604371215
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0540  total reward: -3000.150189367342
  Simulating cascading failure
  ok
timestep 0541  total reward: -3004.229865135452
  Simulating cascading failure
  ok
timestep 0542  total reward: -3007.806697665711
  Simulating cascading failure
  ok
timestep 0543  total reward: -3011.5427020457378
  Simulating cascading failure
  ok
timestep 0544  total reward: -3015.0549940702367
  Simulating cascading failure
  ok
timestep 0545  total reward: -3019.4549727832236
timestep 0546  total reward: -3033.4549727832236
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0547  total reward: -3037.813655165274
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0548  total reward: -3051.813655165274
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0549  total reward: -3054.493906922222
  Simulating cascading failure
  ok
timestep 0550  total reward: -3057.968173219464
  Simulating cascading failure
  ok
timestep 0551  total reward: -3061.5209321473076
timestep 0552  total reward: -3075.5209321473076
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0553  total reward: -3078.0359116999925
  Simulating cascading failure
  ok
timestep 0554  total reward: -3080.388988512702
  Simulating cascading failure
  ok
timestep 0555  total reward: -3082.9824766377587
timestep 0556  total reward: -3096.9824766377587
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0557  total reward: -3098.493750312251
  Simulating cascading failure
  ok
timestep 0558  total reward: -3100.5861708725133
  Simulating cascading failure
  ok
timestep 0559  total reward: -3103.7860092531955
  Simulating cascading failure
  ok
timestep 0560  total reward: -3106.7641269509513
  Simulating cascading failure
  ok
timestep 0561  total reward: -3110.9436422213066
timestep 0562  total reward: -3124.9436422213066
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0563  total reward: -3128.451153909971
  Simulating cascading failure
  ok
timestep 0564  total reward: -3132.111858522098
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0565  total reward: -3146.111858522098
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0566  total reward: -3148.810387232458
  Simulating cascading failure
  ok
timestep 0567  total reward: -3151.2270427882945
  Simulating cascading failure
  ok
timestep 0568  total reward: -3155.5491485501507
  Simulating cascading failure
  ok
timestep 0569  total reward: -3159.489281628333
timestep 0570  total reward: -3173.489281628333
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0571  total reward: -3177.8072373495716
  Simulating cascading failure
  ok
timestep 0572  total reward: -3181.66496687758
  Simulating cascading failure
  ok
timestep 0573  total reward: -3185.6427215622307
  Simulating cascading failure
  ok
timestep 0574  total reward: -3189.090500759138
  Simulating cascading failure
  ok
timestep 0575  total reward: -3193.0493700509405
timestep 0576  total reward: -3207.0493700509405
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0577  total reward: -3209.3312142120835
  Simulating cascading failure
  ok
timestep 0578  total reward: -3211.4378230563734
timestep 0579  total reward: -3225.4378230563734
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0580  total reward: -3226.4792134565973
  Simulating cascading failure
  ok
timestep 0581  total reward: -3227.98430984277
  Simulating cascading failure
  ok
timestep 0582  total reward: -3230.0830884335883
timestep 0583  total reward: -3244.0830884335883
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0584  total reward: -3247.049967758079
  Simulating cascading failure
  ok
timestep 0585  total reward: -3250.2753766175074
timestep 0586  total reward: -3264.2753766175074
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0587  total reward: -3267.8412591457736
  Simulating cascading failure
  ok
timestep 0588  total reward: -3272.4021752403023
timestep 0589  total reward: -3286.4021752403023
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0590  total reward: -3289.9524218912884
  Simulating cascading failure
  ok
timestep 0591  total reward: -3293.4956366158995
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0592  total reward: -3307.4956366158995
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
timestep 0593  total reward: -3321.4956366158995
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0594  total reward: -3325.0345665923683
  Simulating cascading failure
  ok
timestep 0595  total reward: -3328.7823569213024
timestep 0596  total reward: -3342.7823569213024
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0597  total reward: -3345.775206440965
  Simulating cascading failure
  ok
timestep 0598  total reward: -3348.596293051018
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0599  total reward: -3362.596293051018
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0600  total reward: -3376.596293051018
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0601  total reward: -3379.279035033347
  Simulating cascading failure
  ok
timestep 0602  total reward: -3381.9571922044115
  Simulating cascading failure
  ok
timestep 0603  total reward: -3383.7013667334577
  Simulating cascading failure
  ok
timestep 0604  total reward: -3385.317425557775
  Simulating cascading failure
  ok
timestep 0605  total reward: -3386.920305123892
  Simulating cascading failure
  ok
timestep 0606  total reward: -3388.742612213185
  Simulating cascading failure
  ok
timestep 0607  total reward: -3390.908988736448
  Simulating cascading failure
  ok
timestep 0608  total reward: -3395.219889754103
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0609  total reward: -3409.219889754103
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0610  total reward: -3412.9899164573176
  Simulating cascading failure
  ok
timestep 0611  total reward: -3417.0261387486576
  Simulating cascading failure
  ok
timestep 0612  total reward: -3421.1464136423397
  Simulating cascading failure
  ok
timestep 0613  total reward: -3425.9861736754656
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0614  total reward: -3439.9861736754656
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0615  total reward: -3443.405399869267
  Simulating cascading failure
  ok
timestep 0616  total reward: -3448.718297614744
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0617  total reward: -3462.718297614744
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0618  total reward: -3476.718297614744
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0619  total reward: -3479.2710621833235
  Simulating cascading failure
  ok
timestep 0620  total reward: -3482.2736818153535
  Simulating cascading failure
  ok
timestep 0621  total reward: -3486.0916695190326
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0622  total reward: -3500.0916695190326
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0623  total reward: -3502.610050194985
  Simulating cascading failure
  ok
timestep 0624  total reward: -3504.6642132387005
timestep 0625  total reward: -3518.6642132387005
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0626  total reward: -3519.972101758055
  Simulating cascading failure
  ok
timestep 0627  total reward: -3521.1178197855797
timestep 0628  total reward: -3535.1178197855797
Game over! info: The grid is not connexe
timestep 0629  total reward: -3549.1178197855797
Game over! info: The grid is not connexe
timestep 0630  total reward: -3563.1178197855797
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0631  total reward: -3565.1665618787843
  Simulating cascading failure
  ok
timestep 0632  total reward: -3568.5196752174566
  Simulating cascading failure
  ok
timestep 0633  total reward: -3572.2275690803435
  Simulating cascading failure
  ok
timestep 0634  total reward: -3575.332199951828
  Simulating cascading failure
  ok
timestep 0635  total reward: -3578.6032626376873
  Simulating cascading failure
  ok
timestep 0636  total reward: -3582.708449304015
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0637  total reward: -3596.708449304015
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0638  total reward: -3598.887650150723
  Simulating cascading failure
  ok
timestep 0639  total reward: -3601.2061852067627
  Simulating cascading failure
  ok
timestep 0640  total reward: -3602.941164734337
  Simulating cascading failure
  ok
timestep 0641  total reward: -3604.7255705073485
  Simulating cascading failure
  ok
timestep 0642  total reward: -3607.222426587622
  Simulating cascading failure
  ok
timestep 0643  total reward: -3609.946555707438
  Simulating cascading failure
  ok
timestep 0644  total reward: -3612.9180859438493
  Simulating cascading failure
  ok
timestep 0645  total reward: -3615.6125456922164
timestep 0646  total reward: -3629.6125456922164
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0647  total reward: -3631.4675182505252
  Simulating cascading failure
  ok
timestep 0648  total reward: -3633.227065999665
  Simulating cascading failure
  ok
timestep 0649  total reward: -3634.7111577712003
timestep 0650  total reward: -3648.7111577712003
Game over! info: The grid is not connexe
timestep 0651  total reward: -3662.7111577712003
Game over! info: The grid is not connexe
timestep 0652  total reward: -3676.7111577712003
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0653  total reward: -3677.437727328479
  Simulating cascading failure
  ok
timestep 0654  total reward: -3678.324714551422
timestep 0655  total reward: -3692.324714551422
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0656  total reward: -3693.758233478129
  Simulating cascading failure
  ok
timestep 0657  total reward: -3695.432362763728
  Simulating cascading failure
  ok
timestep 0658  total reward: -3697.382038328713
  Simulating cascading failure
  ok
timestep 0659  total reward: -3700.7151306028363
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0660  total reward: -3714.7151306028363
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0661  total reward: -3716.7484512998208
  Simulating cascading failure
  ok
timestep 0662  total reward: -3718.744841818023
  Simulating cascading failure
  ok
timestep 0663  total reward: -3721.2131095765426
  Simulating cascading failure
  ok
timestep 0664  total reward: -3723.3043990487413
  Simulating cascading failure
  ok
timestep 0665  total reward: -3726.3112756994337
  Simulating cascading failure
  ok
timestep 0666  total reward: -3729.9358699454606
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0667  total reward: -3743.9358699454606
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0668  total reward: -3745.5283276945884
  Simulating cascading failure
  ok
timestep 0669  total reward: -3746.8951581736933
timestep 0670  total reward: -3760.8951581736933
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0671  total reward: -3762.2030864258413
  Simulating cascading failure
  ok
timestep 0672  total reward: -3763.8585276864096
  Simulating cascading failure
  ok
timestep 0673  total reward: -3765.9094857218597
timestep 0674  total reward: -3779.9094857218597
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0675  total reward: -3781.219127844755
  Simulating cascading failure
  ok
timestep 0676  total reward: -3782.479087389077
  Simulating cascading failure
  ok
timestep 0677  total reward: -3784.0072759572527
  Simulating cascading failure
  ok
timestep 0678  total reward: -3785.445300791641
  Simulating cascading failure
  ok
timestep 0679  total reward: -3787.333941025214
  Simulating cascading failure
  ok
timestep 0680  total reward: -3790.227410203941
timestep 0681  total reward: -3804.227410203941
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0682  total reward: -3807.345561561675
  Simulating cascading failure
  ok
timestep 0683  total reward: -3811.103096728166
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0684  total reward: -3825.103096728166
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0685  total reward: -3828.430948516837
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0686  total reward: -3842.430948516837
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0687  total reward: -3845.220482100922
  Simulating cascading failure
  ok
timestep 0688  total reward: -3847.622410027977
  Simulating cascading failure
  ok
timestep 0689  total reward: -3849.3458850141756
timestep 0690  total reward: -3863.3458850141756
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0691  total reward: -3866.031894163435
  Simulating cascading failure
  ok
timestep 0692  total reward: -3869.137133521346
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0693  total reward: -3883.137133521346
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0694  total reward: -3885.670638959857
  Simulating cascading failure
  ok
timestep 0695  total reward: -3888.3303392398398
  Simulating cascading failure
  ok
timestep 0696  total reward: -3891.150204421763
  Simulating cascading failure
  ok
timestep 0697  total reward: -3893.580973858882
timestep 0698  total reward: -3907.580973858882
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0699  total reward: -3910.113830995972
  Simulating cascading failure
  ok
timestep 0700  total reward: -3912.4380014741746
  Simulating cascading failure
  ok
timestep 0701  total reward: -3913.9566116983224
  Simulating cascading failure
  ok
timestep 0702  total reward: -3915.806990725928
  Simulating cascading failure
  ok
timestep 0703  total reward: -3918.2498792057972
  Simulating cascading failure
  ok
timestep 0704  total reward: -3922.399847700646
  Simulating cascading failure
  ok
timestep 0705  total reward: -3927.3844939616647
  Simulating cascading failure
  ok
timestep 0706  total reward: -3932.628187781844
timestep 0707  total reward: -3946.628187781844
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0708  total reward: -3960.6281877818437
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0709  total reward: -3974.6281877818437
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
timestep 0710  total reward: -3988.6281877818437
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0711  total reward: -3991.519526049521
  Simulating cascading failure
  ok
timestep 0712  total reward: -3994.7896232233898
  Simulating cascading failure
  ok
timestep 0713  total reward: -3998.370772747059
  Simulating cascading failure
  ok
timestep 0714  total reward: -4003.262413009279
timestep 0715  total reward: -4017.262413009279
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0716  total reward: -4021.121474826672
  Simulating cascading failure
  ok
timestep 0717  total reward: -4024.0173563497647
  Simulating cascading failure
  ok
timestep 0718  total reward: -4027.1117590134772
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0719  total reward: -4041.1117590134772
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
timestep 0720  total reward: -4055.1117590134777
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0721  total reward: -4057.397124923028
  Simulating cascading failure
  ok
timestep 0722  total reward: -4059.4239141543653
  Simulating cascading failure
  ok
timestep 0723  total reward: -4061.5242387833096
timestep 0724  total reward: -4075.5242387833096
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0725  total reward: -4077.0375215363706
  Simulating cascading failure
  ok
timestep 0726  total reward: -4078.7984674740555
  Simulating cascading failure
  ok
timestep 0727  total reward: -4081.2691314730478
  Simulating cascading failure
  ok
timestep 0728  total reward: -4084.640704656518
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0729  total reward: -4098.640704656518
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0730  total reward: -4102.389354995845
  Simulating cascading failure
  ok
timestep 0731  total reward: -4106.522061328731
  Simulating cascading failure
  ok
timestep 0732  total reward: -4111.311246108215
  Simulating cascading failure
  ok
timestep 0733  total reward: -4116.271096650738
timestep 0734  total reward: -4130.271096650738
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0735  total reward: -4133.108578111485
  Simulating cascading failure
  ok
timestep 0736  total reward: -4136.123015611131
timestep 0737  total reward: -4150.123015611131
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0738  total reward: -4164.123015611131
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
timestep 0739  total reward: -4178.123015611131
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0740  total reward: -4181.915660398194
  Simulating cascading failure
  ok
timestep 0741  total reward: -4185.100501450992
  Simulating cascading failure
  ok
timestep 0742  total reward: -4188.572040829092
timestep 0743  total reward: -4202.572040829092
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0744  total reward: -4206.3563951078695
  Simulating cascading failure
  ok
timestep 0745  total reward: -4209.9760392732
  Simulating cascading failure
  ok
timestep 0746  total reward: -4213.253543329105
  Simulating cascading failure
  ok
timestep 0747  total reward: -4216.155751313607
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0748  total reward: -4230.155751313607
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0749  total reward: -4233.072548227631
timestep 0750  total reward: -4247.072548227631
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0751  total reward: -4252.582027898231
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0752  total reward: -4266.58202789823
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0753  total reward: -4273.095703952023
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0754  total reward: -4287.095703952023
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0755  total reward: -4301.095703952023
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0756  total reward: -4315.095703952023
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0757  total reward: -4322.890035406067
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0758  total reward: -4336.890035406067
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0759  total reward: -4350.890035406067
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0760  total reward: -4356.190722375126
  Simulating cascading failure
  ok
timestep 0761  total reward: -4361.466140021395
  Simulating cascading failure
  ok
timestep 0762  total reward: -4368.757215669751
timestep 0763  total reward: -4382.757215669751
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0764  total reward: -4389.041978428557
  Simulating cascading failure
  ok
timestep 0765  total reward: -4393.859574354711
  Simulating cascading failure
  ok
timestep 0766  total reward: -4398.772873122278
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0767  total reward: -4412.772873122278
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0768  total reward: -4417.7249920463855
  Simulating cascading failure
  ok
timestep 0769  total reward: -4422.531609409214
  Simulating cascading failure
  ok
timestep 0770  total reward: -4425.9351955814545
  Simulating cascading failure
  ok
timestep 0771  total reward: -4428.696735805423
  Simulating cascading failure
  ok
timestep 0772  total reward: -4430.616648018039
timestep 0773  total reward: -4444.616648018039
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0774  total reward: -4448.013579528797
  Simulating cascading failure
  ok
timestep 0775  total reward: -4452.709683585648
timestep 0776  total reward: -4466.709683585648
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0777  total reward: -4471.67325339422
  Simulating cascading failure
  ok
timestep 0778  total reward: -4477.8437466679625
timestep 0779  total reward: -4491.8437466679625
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0780  total reward: -4500.772882443157
  Simulating cascading failure
  ok
timestep 0781  total reward: -4510.0835981766695
  Simulating cascading failure
    depth 0: 3 overflowed lines
timestep 0782  total reward: -4524.0835981766695
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0783  total reward: -4538.0835981766695
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0784  total reward: -4552.0835981766695
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0785  total reward: -4566.0835981766695
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0786  total reward: -4572.808866070646
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0787  total reward: -4586.808866070646
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0788  total reward: -4593.368438371717
  Simulating cascading failure
  ok
timestep 0789  total reward: -4598.839600742157
  Simulating cascading failure
  ok
timestep 0790  total reward: -4603.273569032848
  Simulating cascading failure
  ok
timestep 0791  total reward: -4608.157726589159
  Simulating cascading failure
  ok
timestep 0792  total reward: -4613.129093514827
  Simulating cascading failure
  ok
timestep 0793  total reward: -4616.63700534438
  Simulating cascading failure
  ok
timestep 0794  total reward: -4618.874134585832
  Simulating cascading failure
  ok
timestep 0795  total reward: -4621.301107099226
  Simulating cascading failure
  ok
timestep 0796  total reward: -4623.469448214124
  Simulating cascading failure
  ok
timestep 0797  total reward: -4625.813936206372
timestep 0798  total reward: -4639.813936206372
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0799  total reward: -4642.042476882099
  Simulating cascading failure
  ok
timestep 0800  total reward: -4644.444593856087
  Simulating cascading failure
  ok
timestep 0801  total reward: -4648.759967820619
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0802  total reward: -4662.759967820619
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0803  total reward: -4676.759967820619
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0804  total reward: -4690.759967820619
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0805  total reward: -4694.966206098143
  Simulating cascading failure
  ok
timestep 0806  total reward: -4698.87774324296
  Simulating cascading failure
  ok
timestep 0807  total reward: -4702.477822607752
  Simulating cascading failure
  ok
timestep 0808  total reward: -4705.967001237705
  Simulating cascading failure
  ok
timestep 0809  total reward: -4709.935187706588
  Simulating cascading failure
  ok
timestep 0810  total reward: -4715.10616747525
timestep 0811  total reward: -4729.10616747525
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0812  total reward: -4733.45792145304
  Simulating cascading failure
  ok
timestep 0813  total reward: -4737.484932109659
  Simulating cascading failure
  ok
timestep 0814  total reward: -4740.686823958833
  Simulating cascading failure
  ok
timestep 0815  total reward: -4744.590062717176
  Simulating cascading failure
  ok
timestep 0816  total reward: -4749.51507477832
  Simulating cascading failure
  ok
timestep 0817  total reward: -4754.282624825565
  Simulating cascading failure
  ok
timestep 0818  total reward: -4758.379902859653
timestep 0819  total reward: -4772.379902859653
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0820  total reward: -4774.500821333304
  Simulating cascading failure
  ok
timestep 0821  total reward: -4776.508035324589
  Simulating cascading failure
  ok
timestep 0822  total reward: -4779.192365992552
  Simulating cascading failure
  ok
timestep 0823  total reward: -4782.60161849591
  Simulating cascading failure
  ok
timestep 0824  total reward: -4786.341458395003
  Simulating cascading failure
  ok
timestep 0825  total reward: -4792.139086911888
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0826  total reward: -4806.139086911888
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0827  total reward: -4820.139086911888
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0828  total reward: -4823.626570400736
  Simulating cascading failure
  ok
timestep 0829  total reward: -4826.887107552193
  Simulating cascading failure
  ok
timestep 0830  total reward: -4830.207749931987
timestep 0831  total reward: -4844.207749931987
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0832  total reward: -4846.581480954802
  Simulating cascading failure
  ok
timestep 0833  total reward: -4849.098016318842
  Simulating cascading failure
  ok
timestep 0834  total reward: -4852.456941663898
timestep 0835  total reward: -4866.456941663898
Game over! info: The grid is not connexe
timestep 0836  total reward: -4880.456941663898
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0837  total reward: -4882.943052611283
  Simulating cascading failure
  ok
timestep 0838  total reward: -4886.38047225619
  Simulating cascading failure
  ok
timestep 0839  total reward: -4890.91350479866
  Simulating cascading failure
  ok
timestep 0840  total reward: -4896.335654533421
timestep 0841  total reward: -4910.335654533421
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0842  total reward: -4913.18023846291
  Simulating cascading failure
  ok
timestep 0843  total reward: -4916.149358757328
  Simulating cascading failure
  ok
timestep 0844  total reward: -4920.525286385133
  Simulating cascading failure
  ok
timestep 0845  total reward: -4923.535419537764
  Simulating cascading failure
  ok
timestep 0846  total reward: -4928.300358044938
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
timestep 0847  total reward: -4942.300358044938
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0848  total reward: -4946.980860174143
  Simulating cascading failure
  ok
timestep 0849  total reward: -4953.3266561841265
  Simulating cascading failure
  ok
timestep 0850  total reward: -4960.471782660259
  Simulating cascading failure
  ok
timestep 0851  total reward: -4968.492699975708
  Simulating cascading failure
  ok
timestep 0852  total reward: -4978.7265016364045
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0853  total reward: -4992.7265016364045
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0854  total reward: -5006.7265016364045
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0855  total reward: -5011.304149318537
  Simulating cascading failure
  ok
timestep 0856  total reward: -5015.670250311476
  Simulating cascading failure
  ok
timestep 0857  total reward: -5020.588075563797
  Simulating cascading failure
  ok
timestep 0858  total reward: -5025.868576203626
timestep 0859  total reward: -5039.868576203626
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0860  total reward: -5046.360025716698
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0861  total reward: -5060.360025716698
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0862  total reward: -5064.384822420885
  Simulating cascading failure
  ok
timestep 0863  total reward: -5068.363635440655
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0864  total reward: -5082.363635440655
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0865  total reward: -5086.3195642881055
  Simulating cascading failure
  ok
timestep 0866  total reward: -5089.894902609007
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0867  total reward: -5103.894902609007
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0868  total reward: -5106.636662292458
  Simulating cascading failure
  ok
timestep 0869  total reward: -5110.2575908912095
  Simulating cascading failure
  ok
timestep 0870  total reward: -5114.985330517549
timestep 0871  total reward: -5128.985330517549
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0872  total reward: -5134.290197493725
  Simulating cascading failure
  ok
timestep 0873  total reward: -5141.156588726266
timestep 0874  total reward: -5155.156588726266
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0875  total reward: -5169.156588726266
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0876  total reward: -5177.437159049956
  Simulating cascading failure
  ok
timestep 0877  total reward: -5185.6847070113035
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0878  total reward: -5199.6847070113035
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0879  total reward: -5213.6847070113035
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0880  total reward: -5227.6847070113035
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0881  total reward: -5241.6847070113035
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0882  total reward: -5255.6847070113035
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0883  total reward: -5265.155792807154
  Simulating cascading failure
  ok
timestep 0884  total reward: -5273.6987746186005
  Simulating cascading failure
  ok
timestep 0885  total reward: -5280.447315626952
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0886  total reward: -5294.447315626952
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0887  total reward: -5299.736702496764
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0888  total reward: -5313.736702496764
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0889  total reward: -5317.850522428676
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0890  total reward: -5331.850522428676
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0891  total reward: -5345.850522428676
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0892  total reward: -5348.119152062045
  Simulating cascading failure
  ok
timestep 0893  total reward: -5352.02457082797
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0894  total reward: -5366.02457082797
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0895  total reward: -5370.779340138184
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0896  total reward: -5384.779340138184
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0897  total reward: -5398.779340138184
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0898  total reward: -5412.779340138184
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0899  total reward: -5418.996387967575
timestep 0900  total reward: -5432.996387967575
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0901  total reward: -5446.996387967575
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0902  total reward: -5460.996387967575
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0903  total reward: -5466.453873210057
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0904  total reward: -5480.453873210057
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0905  total reward: -5494.453873210057
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0906  total reward: -5502.738350174033
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0907  total reward: -5516.738350174033
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0908  total reward: -5522.549863564887
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0909  total reward: -5536.549863564887
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0910  total reward: -5541.962048764202
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0911  total reward: -5555.962048764202
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0912  total reward: -5569.962048764202
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0913  total reward: -5574.322642372115
  Simulating cascading failure
  ok
timestep 0914  total reward: -5577.856459414867
  Simulating cascading failure
  ok
timestep 0915  total reward: -5581.109273960397
timestep 0916  total reward: -5595.109273960397
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0917  total reward: -5597.886427150706
  Simulating cascading failure
  ok
timestep 0918  total reward: -5601.356167897246
timestep 0919  total reward: -5615.356167897246
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0920  total reward: -5620.616348509043
  Simulating cascading failure
  ok
timestep 0921  total reward: -5627.467951300525
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0922  total reward: -5641.467951300525
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0923  total reward: -5655.467951300525
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0924  total reward: -5669.467951300525
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0925  total reward: -5683.467951300525
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0926  total reward: -5697.467951300525
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0927  total reward: -5703.654713305211
  Simulating cascading failure
  ok
timestep 0928  total reward: -5709.304575948316
  Simulating cascading failure
  ok
timestep 0929  total reward: -5714.173993171952
  Simulating cascading failure
  ok
timestep 0930  total reward: -5719.919889375661
  Simulating cascading failure
  ok
timestep 0931  total reward: -5728.153448078663
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0932  total reward: -5742.153448078663
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0933  total reward: -5746.716210011298
  Simulating cascading failure
  ok
timestep 0934  total reward: -5751.683081905592
timestep 0935  total reward: -5765.683081905592
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0936  total reward: -5770.946959350349
  Simulating cascading failure
  ok
timestep 0937  total reward: -5776.991770870887
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0938  total reward: -5790.991770870887
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0939  total reward: -5793.470015617269
  Simulating cascading failure
  ok
timestep 0940  total reward: -5795.662947365201
  Simulating cascading failure
  ok
timestep 0941  total reward: -5798.257980835048
timestep 0942  total reward: -5812.257980835048
Game over! info: The grid is not connexe
timestep 0943  total reward: -5826.257980835048
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0944  total reward: -5830.977601100825
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0945  total reward: -5844.977601100825
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0946  total reward: -5852.495326095993
  Simulating cascading failure
  ok
timestep 0947  total reward: -5860.885745236049
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 6 overflowed lines
timestep 0948  total reward: -5874.885745236049
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0949  total reward: -5888.885745236049
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0950  total reward: -5902.885745236049
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0951  total reward: -5907.80885449044
  Simulating cascading failure
  ok
timestep 0952  total reward: -5912.063724173435
timestep 0953  total reward: -5926.063724173435
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0954  total reward: -5931.850233568291
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0955  total reward: -5945.850233568291
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 0956  total reward: -5959.850233568291
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0957  total reward: -5965.419710917511
  Simulating cascading failure
  ok
timestep 0958  total reward: -5971.431641955609
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
    depth 2: 5 overflowed lines
timestep 0959  total reward: -5985.431641955609
Game over! info: Cascading failure of depth 3 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0960  total reward: -5999.431641955609
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0961  total reward: -6001.824566003976
  Simulating cascading failure
  ok
timestep 0962  total reward: -6003.82845286745
  Simulating cascading failure
  ok
timestep 0963  total reward: -6005.994240329999
  Simulating cascading failure
  ok
timestep 0964  total reward: -6008.085633223519
timestep 0965  total reward: -6022.085633223519
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0966  total reward: -6024.236268550505
  Simulating cascading failure
  ok
timestep 0967  total reward: -6026.962031520882
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0968  total reward: -6040.962031520882
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0969  total reward: -6044.456658337267
  Simulating cascading failure
  ok
timestep 0970  total reward: -6048.559841367254
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0971  total reward: -6062.559841367254
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0972  total reward: -6066.951682645501
  Simulating cascading failure
  ok
timestep 0973  total reward: -6071.5984882958965
timestep 0974  total reward: -6085.5984882958965
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 0975  total reward: -6099.5984882958965
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0976  total reward: -6105.186932979622
  Simulating cascading failure
  ok
timestep 0977  total reward: -6109.823341785081
  Simulating cascading failure
  ok
timestep 0978  total reward: -6115.374420710109
timestep 0979  total reward: -6129.374420710109
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0980  total reward: -6134.230419327795
  Simulating cascading failure
  ok
timestep 0981  total reward: -6139.976018571709
  Simulating cascading failure
  ok
timestep 0982  total reward: -6145.161235978811
timestep 0983  total reward: -6159.161235978811
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0984  total reward: -6161.522533020463
timestep 0985  total reward: -6175.522533020463
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0986  total reward: -6177.51541587329
  Simulating cascading failure
  ok
timestep 0987  total reward: -6179.317884516051
  Simulating cascading failure
  ok
timestep 0988  total reward: -6181.299086318346
timestep 0989  total reward: -6195.299086318346
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 0990  total reward: -6197.0104923893205
  Simulating cascading failure
  ok
timestep 0991  total reward: -6198.566325964797
  Simulating cascading failure
  ok
timestep 0992  total reward: -6201.930620436019
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 0993  total reward: -6215.930620436019
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 0994  total reward: -6218.9587129205165
  Simulating cascading failure
  ok
timestep 0995  total reward: -6222.612460140973
  Simulating cascading failure
  ok
timestep 0996  total reward: -6226.494117858777
  Simulating cascading failure
  ok
timestep 0997  total reward: -6230.011934586416
  Simulating cascading failure
  ok
timestep 0998  total reward: -6233.818315612986
  Simulating cascading failure
  ok
timestep 0999  total reward: -6238.014082929306
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1000  total reward: -6252.014082929305
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
timestep 1001  total reward: -6266.014082929305
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1002  total reward: -6269.062887776381
  Simulating cascading failure
  ok
timestep 1003  total reward: -6272.159843154266
timestep 1004  total reward: -6286.159843154266
Game over! info: The grid is not connexe
timestep 1005  total reward: -6300.159843154266
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1006  total reward: -6302.5114797013075
  Simulating cascading failure
  ok
timestep 1007  total reward: -6304.9466652001565
  Simulating cascading failure
  ok
timestep 1008  total reward: -6307.594516973602
timestep 1009  total reward: -6321.594516973602
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1010  total reward: -6325.620250340541
  Simulating cascading failure
  ok
timestep 1011  total reward: -6328.808100530657
  Simulating cascading failure
  ok
timestep 1012  total reward: -6331.630245396595
  Simulating cascading failure
  ok
timestep 1013  total reward: -6336.307953676755
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1014  total reward: -6350.307953676755
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1015  total reward: -6354.473971617056
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1016  total reward: -6368.473971617056
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1017  total reward: -6373.448668553767
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1018  total reward: -6387.448668553767
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1019  total reward: -6401.448668553767
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1020  total reward: -6409.693267881984
  Simulating cascading failure
  ok
timestep 1021  total reward: -6419.9002098683495
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1022  total reward: -6433.9002098683495
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1023  total reward: -6438.219856893569
  Simulating cascading failure
  ok
timestep 1024  total reward: -6442.667427631153
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1025  total reward: -6456.667427631153
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1026  total reward: -6461.383163198688
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1027  total reward: -6475.383163198689
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1028  total reward: -6489.383163198689
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1029  total reward: -6494.799978497966
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1030  total reward: -6508.799978497966
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1031  total reward: -6513.075551092092
  Simulating cascading failure
  ok
timestep 1032  total reward: -6517.598615468161
  Simulating cascading failure
  ok
timestep 1033  total reward: -6522.890756191778
  Simulating cascading failure
  ok
timestep 1034  total reward: -6527.977741266741
timestep 1035  total reward: -6541.977741266741
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1036  total reward: -6543.707554404593
  Simulating cascading failure
  ok
timestep 1037  total reward: -6545.55715667513
  Simulating cascading failure
  ok
timestep 1038  total reward: -6549.224685754047
  Simulating cascading failure
  ok
timestep 1039  total reward: -6554.692887688749
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1040  total reward: -6568.692887688749
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1041  total reward: -6582.692887688749
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1042  total reward: -6589.412266881038
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1043  total reward: -6603.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1044  total reward: -6617.412266881038
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1045  total reward: -6631.412266881038
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1046  total reward: -6645.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1047  total reward: -6659.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1048  total reward: -6673.412266881038
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1049  total reward: -6687.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1050  total reward: -6701.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1051  total reward: -6715.412266881038
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1052  total reward: -6729.412266881038
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1053  total reward: -6734.79612962618
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1054  total reward: -6748.79612962618
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1055  total reward: -6753.432729997576
  Simulating cascading failure
  ok
timestep 1056  total reward: -6757.82366342016
  Simulating cascading failure
  ok
timestep 1057  total reward: -6761.854051423477
  Simulating cascading failure
  ok
timestep 1058  total reward: -6765.091884708216
  Simulating cascading failure
  ok
timestep 1059  total reward: -6767.9757687795245
  Simulating cascading failure
  ok
timestep 1060  total reward: -6771.003249948861
  Simulating cascading failure
  ok
timestep 1061  total reward: -6774.310656688134
  Simulating cascading failure
  ok
timestep 1062  total reward: -6778.54129529588
timestep 1063  total reward: -6792.54129529588
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1064  total reward: -6806.54129529588
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1065  total reward: -6820.54129529588
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1066  total reward: -6834.54129529588
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1067  total reward: -6848.54129529588
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1068  total reward: -6862.54129529588
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1069  total reward: -6869.244077183746
  Simulating cascading failure
  ok
timestep 1070  total reward: -6875.732509211293
  Simulating cascading failure
  ok
timestep 1071  total reward: -6881.254821644625
  Simulating cascading failure
  ok
timestep 1072  total reward: -6886.8160179335855
  Simulating cascading failure
  ok
timestep 1073  total reward: -6894.132448842208
  Simulating cascading failure
  ok
timestep 1074  total reward: -6899.62287465805
  Simulating cascading failure
  ok
timestep 1075  total reward: -6905.121257200382
  Simulating cascading failure
  ok
timestep 1076  total reward: -6910.442543555029
  Simulating cascading failure
  ok
timestep 1077  total reward: -6917.441661428929
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1078  total reward: -6931.441661428929
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1079  total reward: -6936.178303592837
  Simulating cascading failure
  ok
timestep 1080  total reward: -6940.805051844485
  Simulating cascading failure
  ok
timestep 1081  total reward: -6944.4291804007335
timestep 1082  total reward: -6958.4291804007335
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1083  total reward: -6960.926777395716
  Simulating cascading failure
  ok
timestep 1084  total reward: -6963.519770787867
  Simulating cascading failure
  ok
timestep 1085  total reward: -6966.265500111164
timestep 1086  total reward: -6980.265500111164
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1087  total reward: -6983.968681924443
timestep 1088  total reward: -6997.968681924443
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1089  total reward: -7011.968681924443
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1090  total reward: -7018.87140469244
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1091  total reward: -7032.87140469244
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1092  total reward: -7040.332833803383
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1093  total reward: -7054.332833803383
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1094  total reward: -7063.963715099574
  Simulating cascading failure
  ok
timestep 1095  total reward: -7072.732965161244
  Simulating cascading failure
  ok
timestep 1096  total reward: -7078.054902544308
  Simulating cascading failure
  ok
timestep 1097  total reward: -7084.38354438209
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1098  total reward: -7098.38354438209
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1099  total reward: -7105.59435169979
  Simulating cascading failure
  ok
timestep 1100  total reward: -7111.936630695412
  Simulating cascading failure
  ok
timestep 1101  total reward: -7118.540340824049
timestep 1102  total reward: -7132.540340824049
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1103  total reward: -7138.605291734101
  Simulating cascading failure
  ok
timestep 1104  total reward: -7144.845737228522
  Simulating cascading failure
  ok
timestep 1105  total reward: -7149.953056465199
timestep 1106  total reward: -7163.953056465199
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1107  total reward: -7166.398681373283
  Simulating cascading failure
  ok
timestep 1108  total reward: -7168.5954209965275
  Simulating cascading failure
  ok
timestep 1109  total reward: -7171.47680188228
  Simulating cascading failure
  ok
timestep 1110  total reward: -7176.007055553339
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
timestep 1111  total reward: -7190.007055553339
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
timestep 1112  total reward: -7204.007055553339
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1113  total reward: -7211.032793295016
  Simulating cascading failure
  ok
timestep 1114  total reward: -7219.11443762303
timestep 1115  total reward: -7233.11443762303
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1116  total reward: -7247.11443762303
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1117  total reward: -7261.11443762303
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1118  total reward: -7267.993693864867
  Simulating cascading failure
  ok
timestep 1119  total reward: -7274.870566801647
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1120  total reward: -7288.870566801646
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1121  total reward: -7293.03391946317
  Simulating cascading failure
  ok
timestep 1122  total reward: -7299.919137266424
  Simulating cascading failure
  ok
timestep 1123  total reward: -7305.579155353477
  Simulating cascading failure
  ok
timestep 1124  total reward: -7311.347017348186
  Simulating cascading failure
  ok
timestep 1125  total reward: -7316.659306930302
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1126  total reward: -7330.659306930302
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1127  total reward: -7335.152234554817
  Simulating cascading failure
  ok
timestep 1128  total reward: -7339.158653209835
  Simulating cascading failure
  ok
timestep 1129  total reward: -7342.448028902318
  Simulating cascading failure
  ok
timestep 1130  total reward: -7345.712827332715
  Simulating cascading failure
  ok
timestep 1131  total reward: -7348.6913203557915
  Simulating cascading failure
  ok
timestep 1132  total reward: -7350.961899062126
timestep 1133  total reward: -7364.961899062126
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1134  total reward: -7367.385358410968
timestep 1135  total reward: -7381.385358410968
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1136  total reward: -7384.752393003209
  Simulating cascading failure
  ok
timestep 1137  total reward: -7388.731645211856
timestep 1138  total reward: -7402.731645211856
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1139  total reward: -7416.731645211856
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1140  total reward: -7430.731645211856
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1141  total reward: -7444.731645211856
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1142  total reward: -7448.896543637701
  Simulating cascading failure
  ok
timestep 1143  total reward: -7452.550859427785
  Simulating cascading failure
  ok
timestep 1144  total reward: -7455.653342618947
  Simulating cascading failure
  ok
timestep 1145  total reward: -7458.920389265399
timestep 1146  total reward: -7472.920389265399
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1147  total reward: -7486.920389265399
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1148  total reward: -7490.740228809822
timestep 1149  total reward: -7504.740228809822
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1150  total reward: -7507.129939900208
  Simulating cascading failure
  ok
timestep 1151  total reward: -7509.940847047551
  Simulating cascading failure
  ok
timestep 1152  total reward: -7513.531982196476
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1153  total reward: -7527.531982196476
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1154  total reward: -7528.9809459626185
  Simulating cascading failure
  ok
timestep 1155  total reward: -7530.818658012509
  Simulating cascading failure
  ok
timestep 1156  total reward: -7532.626177396551
  Simulating cascading failure
  ok
timestep 1157  total reward: -7534.552113319798
  Simulating cascading failure
  ok
timestep 1158  total reward: -7537.308948928538
timestep 1159  total reward: -7551.308948928538
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1160  total reward: -7554.443033227163
  Simulating cascading failure
  ok
timestep 1161  total reward: -7556.940611382935
  Simulating cascading failure
  ok
timestep 1162  total reward: -7558.928585722235
  Simulating cascading failure
  ok
timestep 1163  total reward: -7561.569748121295
  Simulating cascading failure
  ok
timestep 1164  total reward: -7565.196143630744
  Simulating cascading failure
  ok
timestep 1165  total reward: -7569.94923871529
timestep 1166  total reward: -7583.94923871529
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1167  total reward: -7587.283204588845
  Simulating cascading failure
  ok
timestep 1168  total reward: -7590.591837445695
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1169  total reward: -7604.591837445695
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1170  total reward: -7607.188947387748
  Simulating cascading failure
  ok
timestep 1171  total reward: -7610.413027524415
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1172  total reward: -7624.413027524415
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1173  total reward: -7626.792621864146
  Simulating cascading failure
  ok
timestep 1174  total reward: -7630.1559312861245
  Simulating cascading failure
  ok
timestep 1175  total reward: -7633.644066520714
timestep 1176  total reward: -7647.644066520714
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1177  total reward: -7661.644066520714
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1178  total reward: -7664.507756992889
timestep 1179  total reward: -7678.507756992889
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1180  total reward: -7681.270414881479
  Simulating cascading failure
  ok
timestep 1181  total reward: -7684.410358675792
timestep 1182  total reward: -7698.410358675792
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1183  total reward: -7702.304198884083
  Simulating cascading failure
  ok
timestep 1184  total reward: -7707.808811797039
  Simulating cascading failure
  ok
timestep 1185  total reward: -7713.609422470287
  Simulating cascading failure
  ok
timestep 1186  total reward: -7720.333771112276
  Simulating cascading failure
  ok
timestep 1187  total reward: -7727.419108925441
  Simulating cascading failure
  ok
timestep 1188  total reward: -7735.827669321153
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
timestep 1189  total reward: -7749.827669321153
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1190  total reward: -7756.381851509584
  Simulating cascading failure
  ok
timestep 1191  total reward: -7764.12003743757
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1192  total reward: -7778.12003743757
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1193  total reward: -7782.435189932771
  Simulating cascading failure
  ok
timestep 1194  total reward: -7788.2883125926255
  Simulating cascading failure
  ok
timestep 1195  total reward: -7795.555304353942
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1196  total reward: -7809.555304353942
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1197  total reward: -7814.928771589935
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1198  total reward: -7828.928771589935
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1199  total reward: -7833.792327713393
timestep 1200  total reward: -7847.792327713392
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1201  total reward: -7851.389715856594
  Simulating cascading failure
  ok
timestep 1202  total reward: -7855.525513264529
  Simulating cascading failure
  ok
timestep 1203  total reward: -7859.518245257041
  Simulating cascading failure
  ok
timestep 1204  total reward: -7862.397647432885
timestep 1205  total reward: -7876.397647432885
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1206  total reward: -7879.716360357876
  Simulating cascading failure
  ok
timestep 1207  total reward: -7884.461744197761
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1208  total reward: -7898.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1209  total reward: -7912.461744197761
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1210  total reward: -7926.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1211  total reward: -7940.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1212  total reward: -7954.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1213  total reward: -7968.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1214  total reward: -7982.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1215  total reward: -7996.461744197761
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1216  total reward: -8001.560814036652
  Simulating cascading failure
  ok
timestep 1217  total reward: -8007.430341521914
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1218  total reward: -8021.430341521914
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1219  total reward: -8035.430341521914
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1220  total reward: -8049.430341521914
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1221  total reward: -8063.430341521914
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1222  total reward: -8068.384179430122
  Simulating cascading failure
  ok
timestep 1223  total reward: -8074.4205392913855
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1224  total reward: -8088.4205392913855
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1225  total reward: -8090.532571890098
timestep 1226  total reward: -8104.532571890098
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1227  total reward: -8106.150575134991
  Simulating cascading failure
  ok
timestep 1228  total reward: -8108.127299317647
  Simulating cascading failure
  ok
timestep 1229  total reward: -8110.073630713871
  Simulating cascading failure
  ok
timestep 1230  total reward: -8112.582495210321
  Simulating cascading failure
  ok
timestep 1231  total reward: -8115.515732057379
  Simulating cascading failure
  ok
timestep 1232  total reward: -8119.339269704842
timestep 1233  total reward: -8133.339269704842
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1234  total reward: -8135.9860389664145
  Simulating cascading failure
  ok
timestep 1235  total reward: -8138.873134541917
  Simulating cascading failure
  ok
timestep 1236  total reward: -8141.650317920361
  Simulating cascading failure
  ok
timestep 1237  total reward: -8144.453946352526
  Simulating cascading failure
  ok
timestep 1238  total reward: -8149.632404394465
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1239  total reward: -8163.632404394465
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1240  total reward: -8177.632404394465
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1241  total reward: -8180.1434685937165
  Simulating cascading failure
  ok
timestep 1242  total reward: -8182.8035788930365
  Simulating cascading failure
  ok
timestep 1243  total reward: -8186.794642978745
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1244  total reward: -8200.794642978744
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1245  total reward: -8203.919745379651
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1246  total reward: -8217.919745379651
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1247  total reward: -8224.336024769076
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1248  total reward: -8238.336024769076
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1249  total reward: -8248.3003377326
timestep 1250  total reward: -8262.3003377326
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1251  total reward: -8276.3003377326
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1252  total reward: -8282.32037456808
  Simulating cascading failure
  ok
timestep 1253  total reward: -8289.036167464616
  Simulating cascading failure
  ok
timestep 1254  total reward: -8295.579630282778
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
timestep 1255  total reward: -8309.579630282778
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1256  total reward: -8315.23549679075
timestep 1257  total reward: -8329.23549679075
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1258  total reward: -8335.858940568674
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1259  total reward: -8349.858940568674
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1260  total reward: -8354.629170455853
  Simulating cascading failure
  ok
timestep 1261  total reward: -8358.887923597362
  Simulating cascading failure
  ok
timestep 1262  total reward: -8362.888096725983
  Simulating cascading failure
  ok
timestep 1263  total reward: -8366.835414406813
  Simulating cascading failure
  ok
timestep 1264  total reward: -8370.798595885304
  Simulating cascading failure
  ok
timestep 1265  total reward: -8374.149727736462
  Simulating cascading failure
  ok
timestep 1266  total reward: -8376.86982848552
timestep 1267  total reward: -8390.86982848552
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1268  total reward: -8394.063497104553
  Simulating cascading failure
  ok
timestep 1269  total reward: -8398.833014888287
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1270  total reward: -8412.833014888287
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1271  total reward: -8426.833014888287
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1272  total reward: -8440.833014888287
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1273  total reward: -8454.833014888287
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1274  total reward: -8460.992801874345
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1275  total reward: -8474.992801874345
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1276  total reward: -8488.992801874345
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
timestep 1277  total reward: -8502.992801874345
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1278  total reward: -8507.97826853671
  Simulating cascading failure
  ok
timestep 1279  total reward: -8512.441118757028
timestep 1280  total reward: -8526.441118757028
Game over! info: The grid is not connexe
timestep 1281  total reward: -8540.441118757028
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1282  total reward: -8547.423711696918
  Simulating cascading failure
  ok
timestep 1283  total reward: -8555.044457173037
  Simulating cascading failure
  ok
timestep 1284  total reward: -8563.65280089064
  Simulating cascading failure
  ok
timestep 1285  total reward: -8572.090597220284
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1286  total reward: -8586.090597220284
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1287  total reward: -8588.416129514873
  Simulating cascading failure
  ok
timestep 1288  total reward: -8591.395184218585
  Simulating cascading failure
  ok
timestep 1289  total reward: -8593.885636831135
  Simulating cascading failure
  ok
timestep 1290  total reward: -8596.67146367566
  Simulating cascading failure
  ok
timestep 1291  total reward: -8600.190155785735
  Simulating cascading failure
  ok
timestep 1292  total reward: -8605.229343305697
timestep 1293  total reward: -8619.229343305697
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1294  total reward: -8624.147258356377
  Simulating cascading failure
  ok
timestep 1295  total reward: -8629.867663757735
  Simulating cascading failure
  ok
timestep 1296  total reward: -8635.630291639403
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1297  total reward: -8649.630291639403
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1298  total reward: -8663.630291639403
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1299  total reward: -8670.690424431396
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1300  total reward: -8684.690424431396
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1301  total reward: -8688.505508854667
  Simulating cascading failure
  ok
timestep 1302  total reward: -8692.372533623713
  Simulating cascading failure
  ok
timestep 1303  total reward: -8697.788170664138
timestep 1304  total reward: -8711.788170664138
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1305  total reward: -8716.327513150525
  Simulating cascading failure
  ok
timestep 1306  total reward: -8720.808526858877
  Simulating cascading failure
  ok
timestep 1307  total reward: -8724.21403265264
timestep 1308  total reward: -8738.21403265264
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1309  total reward: -8741.321080768419
  Simulating cascading failure
  ok
timestep 1310  total reward: -8744.90042889403
  Simulating cascading failure
  ok
timestep 1311  total reward: -8747.77648379654
  Simulating cascading failure
  ok
timestep 1312  total reward: -8750.602521857263
  Simulating cascading failure
  ok
timestep 1313  total reward: -8753.575821878887
  Simulating cascading failure
  ok
timestep 1314  total reward: -8755.491465215311
timestep 1315  total reward: -8769.491465215311
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1316  total reward: -8770.962330525528
  Simulating cascading failure
  ok
timestep 1317  total reward: -8774.408064190637
  Simulating cascading failure
  ok
timestep 1318  total reward: -8778.539328411736
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1319  total reward: -8792.539328411736
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1320  total reward: -8796.18409089287
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1321  total reward: -8810.18409089287
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1322  total reward: -8813.785723196568
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1323  total reward: -8827.785723196568
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1324  total reward: -8831.007981755043
  Simulating cascading failure
  ok
timestep 1325  total reward: -8835.11819036217
  Simulating cascading failure
  ok
timestep 1326  total reward: -8838.726961681221
  Simulating cascading failure
  ok
timestep 1327  total reward: -8841.403774790055
timestep 1328  total reward: -8855.403774790055
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1329  total reward: -8860.075270144702
  Simulating cascading failure
  ok
timestep 1330  total reward: -8864.33856714352
timestep 1331  total reward: -8878.33856714352
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1332  total reward: -8880.857034350742
  Simulating cascading failure
  ok
timestep 1333  total reward: -8883.643593750963
  Simulating cascading failure
  ok
timestep 1334  total reward: -8889.383760936093
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1335  total reward: -8903.383760936093
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1336  total reward: -8906.46944861138
  Simulating cascading failure
  ok
timestep 1337  total reward: -8910.013614278669
  Simulating cascading failure
  ok
timestep 1338  total reward: -8913.516864572366
  Simulating cascading failure
  ok
timestep 1339  total reward: -8916.023346455993
  Simulating cascading failure
  ok
timestep 1340  total reward: -8918.750780403057
  Simulating cascading failure
  ok
timestep 1341  total reward: -8922.745145869634
  Simulating cascading failure
  ok
timestep 1342  total reward: -8927.55954427244
timestep 1343  total reward: -8941.55954427244
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1344  total reward: -8948.477749421065
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1345  total reward: -8962.477749421065
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1346  total reward: -8976.477749421065
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1347  total reward: -8990.477749421065
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1348  total reward: -9004.477749421065
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1349  total reward: -9009.855974487822
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1350  total reward: -9023.855974487822
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1351  total reward: -9029.63291060008
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 3 overflowed lines
timestep 1352  total reward: -9043.63291060008
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1353  total reward: -9048.34974470338
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1354  total reward: -9062.34974470338
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1355  total reward: -9067.111072654465
timestep 1356  total reward: -9081.111072654465
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1357  total reward: -9084.79003197934
  Simulating cascading failure
  ok
timestep 1358  total reward: -9088.633245030684
  Simulating cascading failure
  ok
timestep 1359  total reward: -9093.370866720677
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1360  total reward: -9107.370866720677
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1361  total reward: -9110.048886072653
  Simulating cascading failure
  ok
timestep 1362  total reward: -9112.356023327475
  Simulating cascading failure
  ok
timestep 1363  total reward: -9114.802383673605
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1364  total reward: -9128.802383673605
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1365  total reward: -9134.055033080844
  Simulating cascading failure
  ok
timestep 1366  total reward: -9140.005699866211
  Simulating cascading failure
  ok
timestep 1367  total reward: -9145.81999220352
  Simulating cascading failure
  ok
timestep 1368  total reward: -9152.415169690978
timestep 1369  total reward: -9166.415169690978
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1370  total reward: -9180.415169690978
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1371  total reward: -9194.415169690978
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1372  total reward: -9208.415169690978
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1373  total reward: -9222.415169690978
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1374  total reward: -9228.136369333937
  Simulating cascading failure
  ok
timestep 1375  total reward: -9233.990653937375
timestep 1376  total reward: -9247.990653937373
Game over! info: The grid is not connexe
timestep 1377  total reward: -9261.990653937373
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1378  total reward: -9270.623286147407
  Simulating cascading failure
  ok
timestep 1379  total reward: -9278.13755238277
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1380  total reward: -9292.13755238277
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1381  total reward: -9306.13755238277
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1382  total reward: -9320.13755238277
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
timestep 1383  total reward: -9334.13755238277
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1384  total reward: -9337.266561238666
  Simulating cascading failure
  ok
timestep 1385  total reward: -9339.748330804781
  Simulating cascading failure
  ok
timestep 1386  total reward: -9342.07206358741
  Simulating cascading failure
  ok
timestep 1387  total reward: -9344.584909468427
timestep 1388  total reward: -9358.584909468427
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1389  total reward: -9363.280434885317
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1390  total reward: -9377.280434885317
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1391  total reward: -9391.280434885317
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1392  total reward: -9405.280434885317
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1393  total reward: -9413.179406521056
  Simulating cascading failure
  ok
timestep 1394  total reward: -9421.67472313223
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1395  total reward: -9435.67472313223
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1396  total reward: -9444.38170549599
  Simulating cascading failure
  ok
timestep 1397  total reward: -9451.677358033368
  Simulating cascading failure
  ok
timestep 1398  total reward: -9458.355477566738
  Simulating cascading failure
  ok
timestep 1399  total reward: -9465.264426018997
  Simulating cascading failure
  ok
timestep 1400  total reward: -9473.798114548226
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1401  total reward: -9487.798114548226
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
timestep 1402  total reward: -9501.798114548226
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1403  total reward: -9515.798114548226
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
timestep 1404  total reward: -9529.798114548226
Game over! info: Cascading failure of depth 2 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1405  total reward: -9535.6967412782
  Simulating cascading failure
  ok
timestep 1406  total reward: -9539.511685488542
  Simulating cascading failure
  ok
timestep 1407  total reward: -9541.124760380517
  Simulating cascading failure
  ok
timestep 1408  total reward: -9542.912668362245
timestep 1409  total reward: -9556.912668362245
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1410  total reward: -9557.786182923966
  Simulating cascading failure
  ok
timestep 1411  total reward: -9558.815203258237
  Simulating cascading failure
  ok
timestep 1412  total reward: -9560.116340572273
  Simulating cascading failure
  ok
timestep 1413  total reward: -9562.86548485815
timestep 1414  total reward: -9576.86548485815
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1415  total reward: -9579.522853493349
  Simulating cascading failure
  ok
timestep 1416  total reward: -9582.547080183096
  Simulating cascading failure
  ok
timestep 1417  total reward: -9585.910334084576
  Simulating cascading failure
  ok
timestep 1418  total reward: -9589.821679372422
  Simulating cascading failure
  ok
timestep 1419  total reward: -9593.762976229964
timestep 1420  total reward: -9607.762976229964
Game over! info: The grid is not connexe
timestep 1421  total reward: -9621.762976229964
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1422  total reward: -9624.224207125411
timestep 1423  total reward: -9638.224207125411
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1424  total reward: -9639.918165263309
timestep 1425  total reward: -9653.918165263309
Game over! info: The grid is not connexe
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1426  total reward: -9667.918165263309
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1427  total reward: -9669.643276188732
  Simulating cascading failure
  ok
timestep 1428  total reward: -9671.565051507587
  Simulating cascading failure
  ok
timestep 1429  total reward: -9673.119470478228
  Simulating cascading failure
  ok
timestep 1430  total reward: -9674.659981497094
  Simulating cascading failure
  ok
timestep 1431  total reward: -9676.60220523399
  Simulating cascading failure
  ok
timestep 1432  total reward: -9678.827082692274
  Simulating cascading failure
  ok
timestep 1433  total reward: -9680.467902113527
timestep 1434  total reward: -9694.467902113527
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1435  total reward: -9695.23298580938
  Simulating cascading failure
  ok
timestep 1436  total reward: -9696.36803436904
  Simulating cascading failure
  ok
timestep 1437  total reward: -9697.798806449555
timestep 1438  total reward: -9711.798806449555
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1439  total reward: -9713.777187813423
timestep 1440  total reward: -9727.777187813423
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1441  total reward: -9730.12403229106
  Simulating cascading failure
  ok
timestep 1442  total reward: -9732.533939593754
timestep 1443  total reward: -9746.533939593754
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1444  total reward: -9748.764382958738
  Simulating cascading failure
  ok
timestep 1445  total reward: -9750.788876588267
  Simulating cascading failure
  ok
timestep 1446  total reward: -9752.235485763278
timestep 1447  total reward: -9766.235485763278
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1448  total reward: -9768.116321723352
  Simulating cascading failure
  ok
timestep 1449  total reward: -9770.030432104446
  Simulating cascading failure
  ok
timestep 1450  total reward: -9771.719900935115
  Simulating cascading failure
  ok
timestep 1451  total reward: -9773.294884356601
  Simulating cascading failure
  ok
timestep 1452  total reward: -9774.851244151776
timestep 1453  total reward: -9788.851244151776
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1454  total reward: -9789.94238497614
  Simulating cascading failure
  ok
timestep 1455  total reward: -9790.659146107468
  Simulating cascading failure
  ok
timestep 1456  total reward: -9791.366863689487
  Simulating cascading failure
  ok
timestep 1457  total reward: -9791.95546718746
  Simulating cascading failure
  ok
timestep 1458  total reward: -9792.815845071194
  Simulating cascading failure
  ok
timestep 1459  total reward: -9793.804439343425
timestep 1460  total reward: -9807.804439343425
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1461  total reward: -9809.332436051678
  Simulating cascading failure
  ok
timestep 1462  total reward: -9811.361522903782
timestep 1463  total reward: -9825.361522903782
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1464  total reward: -9826.810680161325
  Simulating cascading failure
  ok
timestep 1465  total reward: -9828.16946700477
  Simulating cascading failure
  ok
timestep 1466  total reward: -9829.592153959486
timestep 1467  total reward: -9843.592153959486
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1468  total reward: -9845.278017020453
timestep 1469  total reward: -9859.278017020453
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1470  total reward: -9860.810925880953
  Simulating cascading failure
  ok
timestep 1471  total reward: -9862.28374547044
  Simulating cascading failure
  ok
timestep 1472  total reward: -9864.057362757747
  Simulating cascading failure
  ok
timestep 1473  total reward: -9866.11188944168
  Simulating cascading failure
  ok
timestep 1474  total reward: -9867.844984328309
timestep 1475  total reward: -9881.844984328309
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1476  total reward: -9882.825970164104
timestep 1477  total reward: -9896.825970164104
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1478  total reward: -9897.645722366906
  Simulating cascading failure
  ok
timestep 1479  total reward: -9898.252351027524
  Simulating cascading failure
  ok
timestep 1480  total reward: -9898.870585382534
  Simulating cascading failure
  ok
timestep 1481  total reward: -9899.666937017202
  Simulating cascading failure
  ok
timestep 1482  total reward: -9900.42835069316
  Simulating cascading failure
  ok
timestep 1483  total reward: -9901.05874041128
  Simulating cascading failure
  ok
timestep 1484  total reward: -9901.901435219059
timestep 1485  total reward: -9915.901435219059
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1486  total reward: -9917.115086521402
  Simulating cascading failure
  ok
timestep 1487  total reward: -9918.345279687535
  Simulating cascading failure
  ok
timestep 1488  total reward: -9919.388817702082
  Simulating cascading failure
  ok
timestep 1489  total reward: -9920.904796597808
timestep 1490  total reward: -9934.904796597808
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1491  total reward: -9936.058472126206
  Simulating cascading failure
  ok
timestep 1492  total reward: -9937.138090445616
  Simulating cascading failure
  ok
timestep 1493  total reward: -9938.04160082613
  Simulating cascading failure
  ok
timestep 1494  total reward: -9939.172873413572
  Simulating cascading failure
  ok
timestep 1495  total reward: -9940.298669296862
  Simulating cascading failure
  ok
timestep 1496  total reward: -9941.755352337761
timestep 1497  total reward: -9955.755352337761
Game over! info: The grid is not connexe
timestep 1498  total reward: -9969.755352337761
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1499  total reward: -9970.991997798421
timestep 1500  total reward: -9984.991997798421
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1501  total reward: -9985.936987264406
  Simulating cascading failure
  ok
timestep 1502  total reward: -9987.49542855444
timestep 1503  total reward: -10001.49542855444
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1504  total reward: -10002.474459733623
  Simulating cascading failure
  ok
timestep 1505  total reward: -10003.337456116304
  Simulating cascading failure
  ok
timestep 1506  total reward: -10004.05844256145
  Simulating cascading failure
  ok
timestep 1507  total reward: -10004.798868101865
  Simulating cascading failure
  ok
timestep 1508  total reward: -10006.27490429903
  Simulating cascading failure
  ok
timestep 1509  total reward: -10008.438237340151
timestep 1510  total reward: -10022.438237340151
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1511  total reward: -10024.143560474191
  Simulating cascading failure
  ok
timestep 1512  total reward: -10025.891643740817
  Simulating cascading failure
  ok
timestep 1513  total reward: -10028.303762780051
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1514  total reward: -10042.303762780051
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1515  total reward: -10044.093680538368
  Simulating cascading failure
  ok
timestep 1516  total reward: -10045.908649060617
  Simulating cascading failure
  ok
timestep 1517  total reward: -10047.542227184493
  Simulating cascading failure
  ok
timestep 1518  total reward: -10049.146190167394
  Simulating cascading failure
  ok
timestep 1519  total reward: -10051.053526694868
timestep 1520  total reward: -10065.053526694868
Game over! info: The grid is not connexe
timestep 1521  total reward: -10079.053526694868
Game over! info: The grid is not connexe
timestep 1522  total reward: -10093.053526694868
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1523  total reward: -10094.58204901391
  Simulating cascading failure
  ok
timestep 1524  total reward: -10095.864784703404
  Simulating cascading failure
  ok
timestep 1525  total reward: -10097.599280047023
  Simulating cascading failure
  ok
timestep 1526  total reward: -10099.956282159379
timestep 1527  total reward: -10113.956282159379
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1528  total reward: -10115.032386099114
  Simulating cascading failure
  ok
timestep 1529  total reward: -10115.897561187967
  Simulating cascading failure
  ok
timestep 1530  total reward: -10116.777482051704
  Simulating cascading failure
  ok
timestep 1531  total reward: -10117.502469250416
  Simulating cascading failure
  ok
timestep 1532  total reward: -10118.436700316215
  Simulating cascading failure
  ok
timestep 1533  total reward: -10119.881117241157
timestep 1534  total reward: -10133.881117241157
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1535  total reward: -10135.630745633287
  Simulating cascading failure
  ok
timestep 1536  total reward: -10138.773163258056
  Simulating cascading failure
  ok
timestep 1537  total reward: -10142.320434165496
  Simulating cascading failure
  ok
timestep 1538  total reward: -10147.155812424124
  Simulating cascading failure
  ok
timestep 1539  total reward: -10152.36913151426
timestep 1540  total reward: -10166.36913151426
Game over! info: The grid is not connexe
timestep 1541  total reward: -10180.36913151426
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1542  total reward: -10181.863162612703
  Simulating cascading failure
  ok
timestep 1543  total reward: -10183.536866382263
timestep 1544  total reward: -10197.536866382263
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1545  total reward: -10199.622755951736
  Simulating cascading failure
  ok
timestep 1546  total reward: -10202.356886940788
  Simulating cascading failure
  ok
timestep 1547  total reward: -10204.748446315018
  Simulating cascading failure
  ok
timestep 1548  total reward: -10207.102246761217
  Simulating cascading failure
  ok
timestep 1549  total reward: -10209.503088165886
  Simulating cascading failure
  ok
timestep 1550  total reward: -10211.698869634927
  Simulating cascading failure
  ok
timestep 1551  total reward: -10213.849626458226
  Simulating cascading failure
  ok
timestep 1552  total reward: -10215.716271828427
timestep 1553  total reward: -10229.716271828427
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1554  total reward: -10230.50223348592
  Simulating cascading failure
  ok
timestep 1555  total reward: -10231.421486706207
  Simulating cascading failure
  ok
timestep 1556  total reward: -10232.612463054893
  Simulating cascading failure
  ok
timestep 1557  total reward: -10234.723591932241
  Simulating cascading failure
  ok
timestep 1558  total reward: -10237.206172216762
timestep 1559  total reward: -10251.206172216762
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1560  total reward: -10253.497561580638
  Simulating cascading failure
  ok
timestep 1561  total reward: -10255.84142104747
  Simulating cascading failure
  ok
timestep 1562  total reward: -10258.386852514086
  Simulating cascading failure
  ok
timestep 1563  total reward: -10262.35835542338
  Simulating cascading failure
  ok
timestep 1564  total reward: -10266.83218555816
timestep 1565  total reward: -10280.83218555816
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1566  total reward: -10282.28585933225
  Simulating cascading failure
  ok
timestep 1567  total reward: -10283.844534676782
  Simulating cascading failure
  ok
timestep 1568  total reward: -10285.539379875367
  Simulating cascading failure
  ok
timestep 1569  total reward: -10287.616753716753
  Simulating cascading failure
  ok
timestep 1570  total reward: -10289.844853766277
  Simulating cascading failure
  ok
timestep 1571  total reward: -10291.83359601074
timestep 1572  total reward: -10305.83359601074
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1573  total reward: -10307.430688865797
timestep 1574  total reward: -10321.430688865797
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1575  total reward: -10322.714693216774
  Simulating cascading failure
  ok
timestep 1576  total reward: -10324.152439337075
  Simulating cascading failure
  ok
timestep 1577  total reward: -10325.450478791008
  Simulating cascading failure
  ok
timestep 1578  total reward: -10327.083896225078
  Simulating cascading failure
  ok
timestep 1579  total reward: -10328.993679374384
  Simulating cascading failure
  ok
timestep 1580  total reward: -10331.564327002301
timestep 1581  total reward: -10345.564327002301
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1582  total reward: -10347.583450400642
timestep 1583  total reward: -10361.583450400642
Game over! info: The grid is not connexe
timestep 1584  total reward: -10375.583450400643
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1585  total reward: -10378.059372540916
  Simulating cascading failure
  ok
timestep 1586  total reward: -10380.468951472947
  Simulating cascading failure
  ok
timestep 1587  total reward: -10382.782076066836
  Simulating cascading failure
  ok
timestep 1588  total reward: -10385.389520845147
  Simulating cascading failure
  ok
timestep 1589  total reward: -10387.58366829609
timestep 1590  total reward: -10401.58366829609
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1591  total reward: -10404.123233857856
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1592  total reward: -10418.123233857856
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1593  total reward: -10419.743519764932
  Simulating cascading failure
  ok
timestep 1594  total reward: -10421.285383262682
  Simulating cascading failure
  ok
timestep 1595  total reward: -10423.190547231901
  Simulating cascading failure
  ok
timestep 1596  total reward: -10424.942819477055
  Simulating cascading failure
  ok
timestep 1597  total reward: -10426.774545574883
  Simulating cascading failure
  ok
timestep 1598  total reward: -10428.750094161478
  Simulating cascading failure
  ok
timestep 1599  total reward: -10435.599209562999
timestep 1600  total reward: -10449.599209562999
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1601  total reward: -10450.441447540765
  Simulating cascading failure
  ok
timestep 1602  total reward: -10451.25145213258
  Simulating cascading failure
  ok
timestep 1603  total reward: -10452.176747253288
  Simulating cascading failure
  ok
timestep 1604  total reward: -10452.990105566514
  Simulating cascading failure
  ok
timestep 1605  total reward: -10454.276611059631
timestep 1606  total reward: -10468.276611059631
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1607  total reward: -10470.276211286595
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1608  total reward: -10484.276211286595
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1609  total reward: -10486.490676573834
timestep 1610  total reward: -10500.490676573834
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1611  total reward: -10502.498067758557
  Simulating cascading failure
  ok
timestep 1612  total reward: -10504.215515089589
timestep 1613  total reward: -10518.215515089589
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1614  total reward: -10519.754512347517
  Simulating cascading failure
  ok
timestep 1615  total reward: -10521.304859889744
  Simulating cascading failure
  ok
timestep 1616  total reward: -10523.231843505091
  Simulating cascading failure
  ok
timestep 1617  total reward: -10526.241152514163
  Simulating cascading failure
  ok
timestep 1618  total reward: -10528.671873302663
  Simulating cascading failure
  ok
timestep 1619  total reward: -10530.781852589109
  Simulating cascading failure
  ok
timestep 1620  total reward: -10533.50337277916
  Simulating cascading failure
  ok
timestep 1621  total reward: -10535.65260281742
  Simulating cascading failure
  ok
timestep 1622  total reward: -10537.33487124962
  Simulating cascading failure
  ok
timestep 1623  total reward: -10538.774413849915
  Simulating cascading failure
  ok
timestep 1624  total reward: -10539.980341544546
timestep 1625  total reward: -10553.980341544546
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1626  total reward: -10554.607624570428
  Simulating cascading failure
  ok
timestep 1627  total reward: -10555.430057498786
  Simulating cascading failure
  ok
timestep 1628  total reward: -10556.320022617152
  Simulating cascading failure
  ok
timestep 1629  total reward: -10558.319628935762
  Simulating cascading failure
  ok
timestep 1630  total reward: -10560.27876563141
  Simulating cascading failure
  ok
timestep 1631  total reward: -10561.912795365224
  Simulating cascading failure
  ok
timestep 1632  total reward: -10564.452270470058
  Simulating cascading failure
  ok
timestep 1633  total reward: -10567.402083886835
  Simulating cascading failure
  ok
timestep 1634  total reward: -10571.00237719225
  Simulating cascading failure
  ok
timestep 1635  total reward: -10574.237404537209
timestep 1636  total reward: -10588.237404537209
Game over! info: The grid is not connexe
timestep 1637  total reward: -10602.237404537209
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1638  total reward: -10603.208474835177
timestep 1639  total reward: -10617.208474835177
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1640  total reward: -10618.35570404294
  Simulating cascading failure
  ok
timestep 1641  total reward: -10619.652057493124
  Simulating cascading failure
  ok
timestep 1642  total reward: -10620.867229643518
  Simulating cascading failure
  ok
timestep 1643  total reward: -10621.962672747726
  Simulating cascading failure
  ok
timestep 1644  total reward: -10623.123032584535
  Simulating cascading failure
  ok
timestep 1645  total reward: -10624.353685316633
  Simulating cascading failure
  ok
timestep 1646  total reward: -10625.279505039696
  Simulating cascading failure
  ok
timestep 1647  total reward: -10626.047231861958
  Simulating cascading failure
  ok
timestep 1648  total reward: -10626.803134519057
timestep 1649  total reward: -10640.803134519057
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1650  total reward: -10641.198490513636
  Simulating cascading failure
  ok
timestep 1651  total reward: -10641.65646150165
  Simulating cascading failure
  ok
timestep 1652  total reward: -10642.406653862186
  Simulating cascading failure
  ok
timestep 1653  total reward: -10643.183744081232
timestep 1654  total reward: -10657.183744081232
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1655  total reward: -10659.049983450856
  Simulating cascading failure
  ok
timestep 1656  total reward: -10660.626024926045
timestep 1657  total reward: -10674.626024926045
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1658  total reward: -10675.769672389686
  Simulating cascading failure
  ok
timestep 1659  total reward: -10676.906513568767
  Simulating cascading failure
  ok
timestep 1660  total reward: -10678.531191994869
  Simulating cascading failure
  ok
timestep 1661  total reward: -10679.966614530433
  Simulating cascading failure
  ok
timestep 1662  total reward: -10681.10425291111
  Simulating cascading failure
  ok
timestep 1663  total reward: -10682.281586490679
  Simulating cascading failure
  ok
timestep 1664  total reward: -10683.357403725597
  Simulating cascading failure
  ok
timestep 1665  total reward: -10684.634867021474
  Simulating cascading failure
  ok
timestep 1666  total reward: -10685.78758768252
  Simulating cascading failure
  ok
timestep 1667  total reward: -10686.67567696171
  Simulating cascading failure
  ok
timestep 1668  total reward: -10687.886572284027
  Simulating cascading failure
  ok
timestep 1669  total reward: -10689.171610777961
timestep 1670  total reward: -10703.171610777961
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1671  total reward: -10704.411193163625
  Simulating cascading failure
  ok
timestep 1672  total reward: -10705.307535467215
  Simulating cascading failure
  ok
timestep 1673  total reward: -10706.15916244897
  Simulating cascading failure
  ok
timestep 1674  total reward: -10706.886074358012
  Simulating cascading failure
  ok
timestep 1675  total reward: -10707.579979713082
  Simulating cascading failure
  ok
timestep 1676  total reward: -10708.586319150847
  Simulating cascading failure
  ok
timestep 1677  total reward: -10710.219812559437
  Simulating cascading failure
  ok
timestep 1678  total reward: -10712.29142524301
timestep 1679  total reward: -10726.29142524301
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1680  total reward: -10727.996695842834
  Simulating cascading failure
  ok
timestep 1681  total reward: -10730.06040709314
  Simulating cascading failure
  ok
timestep 1682  total reward: -10731.65764998104
  Simulating cascading failure
  ok
timestep 1683  total reward: -10733.371736587153
  Simulating cascading failure
  ok
timestep 1684  total reward: -10735.211588594724
  Simulating cascading failure
  ok
timestep 1685  total reward: -10736.72570611135
  Simulating cascading failure
  ok
timestep 1686  total reward: -10738.763589186514
  Simulating cascading failure
  ok
timestep 1687  total reward: -10740.674331120996
  Simulating cascading failure
  ok
timestep 1688  total reward: -10742.246573682081
  Simulating cascading failure
  ok
timestep 1689  total reward: -10744.27973251695
  Simulating cascading failure
  ok
timestep 1690  total reward: -10746.940063236856
  Simulating cascading failure
  ok
timestep 1691  total reward: -10749.864435232179
  Simulating cascading failure
  ok
timestep 1692  total reward: -10752.6792564954
timestep 1693  total reward: -10766.6792564954
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1694  total reward: -10768.618168886744
  Simulating cascading failure
  ok
timestep 1695  total reward: -10770.717158028467
  Simulating cascading failure
  ok
timestep 1696  total reward: -10772.705698441132
timestep 1697  total reward: -10786.705698441132
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1698  total reward: -10787.654424144268
  Simulating cascading failure
  ok
timestep 1699  total reward: -10788.72709887924
  Simulating cascading failure
  ok
timestep 1700  total reward: -10790.162791686333
  Simulating cascading failure
  ok
timestep 1701  total reward: -10791.726824074287
  Simulating cascading failure
  ok
timestep 1702  total reward: -10793.880265057065
  Simulating cascading failure
  ok
timestep 1703  total reward: -10796.30823822041
  Simulating cascading failure
  ok
timestep 1704  total reward: -10798.9168762221
  Simulating cascading failure
  ok
timestep 1705  total reward: -10802.944999421126
  Simulating cascading failure
  ok
timestep 1706  total reward: -10807.478539455362
  Simulating cascading failure
  ok
timestep 1707  total reward: -10813.139627716282
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1708  total reward: -10827.139627716282
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1709  total reward: -10828.722959595592
  Simulating cascading failure
  ok
timestep 1710  total reward: -10830.79269117504
  Simulating cascading failure
  ok
timestep 1711  total reward: -10832.446413524507
  Simulating cascading failure
  ok
timestep 1712  total reward: -10834.429299102063
  Simulating cascading failure
  ok
timestep 1713  total reward: -10836.70980048532
  Simulating cascading failure
  ok
timestep 1714  total reward: -10839.01545767816
  Simulating cascading failure
  ok
timestep 1715  total reward: -10841.200556891123
  Simulating cascading failure
  ok
timestep 1716  total reward: -10842.714386185402
  Simulating cascading failure
  ok
timestep 1717  total reward: -10844.339086443473
  Simulating cascading failure
  ok
timestep 1718  total reward: -10846.003346668025
  Simulating cascading failure
  ok
timestep 1719  total reward: -10847.34313788575
  Simulating cascading failure
  ok
timestep 1720  total reward: -10848.408409603684
  Simulating cascading failure
  ok
timestep 1721  total reward: -10849.508087452694
timestep 1722  total reward: -10863.508087452694
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1723  total reward: -10864.495129316465
  Simulating cascading failure
  ok
timestep 1724  total reward: -10865.610553712406
  Simulating cascading failure
  ok
timestep 1725  total reward: -10867.266195433625
  Simulating cascading failure
  ok
timestep 1726  total reward: -10869.197015418416
  Simulating cascading failure
  ok
timestep 1727  total reward: -10871.451962319306
  Simulating cascading failure
  ok
timestep 1728  total reward: -10875.34265806392
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1729  total reward: -10889.34265806392
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1730  total reward: -10891.717383353222
  Simulating cascading failure
  ok
timestep 1731  total reward: -10894.662594646366
  Simulating cascading failure
  ok
timestep 1732  total reward: -10897.52319408191
  Simulating cascading failure
  ok
timestep 1733  total reward: -10899.789668304393
timestep 1734  total reward: -10913.789668304393
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1735  total reward: -10916.218816998515
  Simulating cascading failure
  ok
timestep 1736  total reward: -10919.198431893823
  Simulating cascading failure
  ok
timestep 1737  total reward: -10922.623297904156
  Simulating cascading failure
  ok
timestep 1738  total reward: -10926.103870028894
  Simulating cascading failure
  ok
timestep 1739  total reward: -10928.943829009137
  Simulating cascading failure
  ok
timestep 1740  total reward: -10932.46216162167
  Simulating cascading failure
  ok
timestep 1741  total reward: -10935.70460942197
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1742  total reward: -10949.70460942197
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1743  total reward: -10951.361278093107
  Simulating cascading failure
  ok
timestep 1744  total reward: -10952.616419697792
  Simulating cascading failure
  ok
timestep 1745  total reward: -10953.732314460793
  Simulating cascading failure
  ok
timestep 1746  total reward: -10955.030189876226
  Simulating cascading failure
  ok
timestep 1747  total reward: -10956.40300911167
timestep 1748  total reward: -10970.40300911167
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1749  total reward: -10971.75547625735
timestep 1750  total reward: -10985.75547625735
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1751  total reward: -10987.821375152329
  Simulating cascading failure
  ok
timestep 1752  total reward: -10990.848386964497
  Simulating cascading failure
  ok
timestep 1753  total reward: -10993.752568810463
  Simulating cascading failure
  ok
timestep 1754  total reward: -10995.998383742623
  Simulating cascading failure
  ok
timestep 1755  total reward: -10998.493037541857
timestep 1756  total reward: -11012.493037541857
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1757  total reward: -11014.224547054413
  Simulating cascading failure
  ok
timestep 1758  total reward: -11016.178633205498
timestep 1759  total reward: -11030.178633205498
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1760  total reward: -11032.548866541354
  Simulating cascading failure
  ok
timestep 1761  total reward: -11035.533641716307
  Simulating cascading failure
  ok
timestep 1762  total reward: -11038.49666276691
  Simulating cascading failure
  ok
timestep 1763  total reward: -11041.120946255618
timestep 1764  total reward: -11055.120946255618
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1765  total reward: -11056.715367999992
timestep 1766  total reward: -11070.715367999992
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1767  total reward: -11072.025362620854
  Simulating cascading failure
  ok
timestep 1768  total reward: -11073.052554709246
  Simulating cascading failure
  ok
timestep 1769  total reward: -11073.888855401015
  Simulating cascading failure
  ok
timestep 1770  total reward: -11074.614311258247
  Simulating cascading failure
  ok
timestep 1771  total reward: -11075.484774802055
  Simulating cascading failure
  ok
timestep 1772  total reward: -11076.650131885512
  Simulating cascading failure
  ok
timestep 1773  total reward: -11078.193556985849
timestep 1774  total reward: -11092.193556985849
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1775  total reward: -11094.426579700852
  Simulating cascading failure
  ok
timestep 1776  total reward: -11097.43117453484
  Simulating cascading failure
  ok
timestep 1777  total reward: -11100.037283592472
  Simulating cascading failure
  ok
timestep 1778  total reward: -11102.997656457113
  Simulating cascading failure
  ok
timestep 1779  total reward: -11106.27062778869
  Simulating cascading failure
  ok
timestep 1780  total reward: -11109.39560242645
timestep 1781  total reward: -11123.39560242645
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1782  total reward: -11124.806220979552
  Simulating cascading failure
  ok
timestep 1783  total reward: -11126.467528063451
  Simulating cascading failure
  ok
timestep 1784  total reward: -11129.29596036599
timestep 1785  total reward: -11143.29596036599
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1786  total reward: -11145.414699732435
  Simulating cascading failure
  ok
timestep 1787  total reward: -11147.576193829957
  Simulating cascading failure
  ok
timestep 1788  total reward: -11149.016887113397
  Simulating cascading failure
  ok
timestep 1789  total reward: -11150.626223886093
  Simulating cascading failure
  ok
timestep 1790  total reward: -11152.531059547655
  Simulating cascading failure
  ok
timestep 1791  total reward: -11154.051831990926
  Simulating cascading failure
  ok
timestep 1792  total reward: -11155.375397006595
  Simulating cascading failure
  ok
timestep 1793  total reward: -11156.48777806754
  Simulating cascading failure
  ok
timestep 1794  total reward: -11157.508984917142
  Simulating cascading failure
  ok
timestep 1795  total reward: -11158.763245437623
timestep 1796  total reward: -11172.763245437623
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1797  total reward: -11173.621676294513
  Simulating cascading failure
  ok
timestep 1798  total reward: -11174.719087397589
  Simulating cascading failure
  ok
timestep 1799  total reward: -11176.082321076188
  Simulating cascading failure
  ok
timestep 1800  total reward: -11177.65147206151
  Simulating cascading failure
  ok
timestep 1801  total reward: -11180.008916075369
  Simulating cascading failure
  ok
timestep 1802  total reward: -11181.714697931198
  Simulating cascading failure
  ok
timestep 1803  total reward: -11183.285465293553
  Simulating cascading failure
  ok
timestep 1804  total reward: -11184.87125492737
timestep 1805  total reward: -11198.87125492737
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1806  total reward: -11200.028150788254
  Simulating cascading failure
  ok
timestep 1807  total reward: -11201.29606555303
  Simulating cascading failure
  ok
timestep 1808  total reward: -11202.55417141316
  Simulating cascading failure
  ok
timestep 1809  total reward: -11203.96211263089
  Simulating cascading failure
  ok
timestep 1810  total reward: -11205.39042217224
  Simulating cascading failure
  ok
timestep 1811  total reward: -11207.450887135841
  Simulating cascading failure
  ok
timestep 1812  total reward: -11209.464038814476
timestep 1813  total reward: -11223.464038814476
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1814  total reward: -11224.365540757146
  Simulating cascading failure
  ok
timestep 1815  total reward: -11225.012754014797
  Simulating cascading failure
  ok
timestep 1816  total reward: -11225.549619269397
  Simulating cascading failure
  ok
timestep 1817  total reward: -11225.994610082467
  Simulating cascading failure
  ok
timestep 1818  total reward: -11226.451867612097
timestep 1819  total reward: -11240.451867612097
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1820  total reward: -11241.110332459179
  Simulating cascading failure
  ok
timestep 1821  total reward: -11241.891553253397
  Simulating cascading failure
  ok
timestep 1822  total reward: -11242.868063930498
  Simulating cascading failure
  ok
timestep 1823  total reward: -11243.997419925943
  Simulating cascading failure
  ok
timestep 1824  total reward: -11245.864375241868
timestep 1825  total reward: -11259.864375241868
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1826  total reward: -11261.217129390243
  Simulating cascading failure
  ok
timestep 1827  total reward: -11262.611044458496
  Simulating cascading failure
  ok
timestep 1828  total reward: -11263.824803114674
  Simulating cascading failure
  ok
timestep 1829  total reward: -11264.95711436768
  Simulating cascading failure
  ok
timestep 1830  total reward: -11265.98301242279
  Simulating cascading failure
  ok
timestep 1831  total reward: -11267.507543219208
  Simulating cascading failure
  ok
timestep 1832  total reward: -11268.713694757695
  Simulating cascading failure
  ok
timestep 1833  total reward: -11270.068563887085
  Simulating cascading failure
  ok
timestep 1834  total reward: -11271.075705768078
  Simulating cascading failure
  ok
timestep 1835  total reward: -11272.001558147196
  Simulating cascading failure
  ok
timestep 1836  total reward: -11272.988734856808
  Simulating cascading failure
  ok
timestep 1837  total reward: -11273.947825731913
  Simulating cascading failure
  ok
timestep 1838  total reward: -11275.015119128631
  Simulating cascading failure
  ok
timestep 1839  total reward: -11276.385693326692
  Simulating cascading failure
  ok
timestep 1840  total reward: -11277.671383332934
  Simulating cascading failure
  ok
timestep 1841  total reward: -11278.421769824337
  Simulating cascading failure
  ok
timestep 1842  total reward: -11279.08398185646
  Simulating cascading failure
  ok
timestep 1843  total reward: -11279.911140718601
timestep 1844  total reward: -11293.911140718601
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1845  total reward: -11295.248899856953
  Simulating cascading failure
  ok
timestep 1846  total reward: -11296.773527943693
  Simulating cascading failure
  ok
timestep 1847  total reward: -11299.60077762309
  Simulating cascading failure
  ok
timestep 1848  total reward: -11301.601148710888
  Simulating cascading failure
  ok
timestep 1849  total reward: -11303.485060300642
timestep 1850  total reward: -11317.485060300642
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1851  total reward: -11319.607259020286
  Simulating cascading failure
  ok
timestep 1852  total reward: -11321.37683436354
  Simulating cascading failure
  ok
timestep 1853  total reward: -11323.108613790737
  Simulating cascading failure
  ok
timestep 1854  total reward: -11324.796553764956
timestep 1855  total reward: -11338.796553764956
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1856  total reward: -11340.465094296154
  Simulating cascading failure
  ok
timestep 1857  total reward: -11342.372616667264
timestep 1858  total reward: -11356.372616667264
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1859  total reward: -11357.380756950162
  Simulating cascading failure
  ok
timestep 1860  total reward: -11358.832611167032
  Simulating cascading failure
  ok
timestep 1861  total reward: -11360.505491617863
  Simulating cascading failure
  ok
timestep 1862  total reward: -11362.061982901847
  Simulating cascading failure
  ok
timestep 1863  total reward: -11364.028070614746
timestep 1864  total reward: -11378.028070614746
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1865  total reward: -11378.892997439174
timestep 1866  total reward: -11392.892997439174
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1867  total reward: -11393.819859877012
  Simulating cascading failure
  ok
timestep 1868  total reward: -11395.061364332356
  Simulating cascading failure
  ok
timestep 1869  total reward: -11396.300047973311
  Simulating cascading failure
  ok
timestep 1870  total reward: -11397.822986939933
  Simulating cascading failure
  ok
timestep 1871  total reward: -11400.374117868614
  Simulating cascading failure
  ok
timestep 1872  total reward: -11403.190389775507
timestep 1873  total reward: -11417.190389775507
Game over! info: The grid is not connexe
timestep 1874  total reward: -11431.190389775507
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1875  total reward: -11433.211379361474
  Simulating cascading failure
  ok
timestep 1876  total reward: -11435.0852208865
  Simulating cascading failure
  ok
timestep 1877  total reward: -11436.723351062314
timestep 1878  total reward: -11450.723351062314
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1879  total reward: -11452.08755035526
  Simulating cascading failure
  ok
timestep 1880  total reward: -11453.806943019783
  Simulating cascading failure
  ok
timestep 1881  total reward: -11456.170519655969
  Simulating cascading failure
  ok
timestep 1882  total reward: -11458.57659841191
  Simulating cascading failure
  ok
timestep 1883  total reward: -11460.676888686936
  Simulating cascading failure
  ok
timestep 1884  total reward: -11463.945222015283
  Simulating cascading failure
  ok
timestep 1885  total reward: -11467.987952015477
  Simulating cascading failure
  ok
timestep 1886  total reward: -11471.660488206247
timestep 1887  total reward: -11485.660488206247
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1888  total reward: -11487.065564687682
  Simulating cascading failure
  ok
timestep 1889  total reward: -11488.233273216414
  Simulating cascading failure
  ok
timestep 1890  total reward: -11489.684390934726
timestep 1891  total reward: -11503.684390934726
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1892  total reward: -11505.288415459738
  Simulating cascading failure
  ok
timestep 1893  total reward: -11507.350430513165
  Simulating cascading failure
  ok
timestep 1894  total reward: -11510.903414255026
  Simulating cascading failure
  ok
timestep 1895  total reward: -11514.868731042767
  Simulating cascading failure
  ok
timestep 1896  total reward: -11517.203742527065
  Simulating cascading failure
  ok
timestep 1897  total reward: -11519.776924334996
timestep 1898  total reward: -11533.776924334996
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1899  total reward: -11535.826711132016
  Simulating cascading failure
  ok
timestep 1900  total reward: -11537.766446755028
  Simulating cascading failure
  ok
timestep 1901  total reward: -11540.25404652574
timestep 1902  total reward: -11554.25404652574
Game over! info: The grid is not connexe
timestep 1903  total reward: -11568.25404652574
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1904  total reward: -11570.703302266435
  Simulating cascading failure
  ok
timestep 1905  total reward: -11573.448466253232
  Simulating cascading failure
  ok
timestep 1906  total reward: -11575.247285397374
timestep 1907  total reward: -11589.247285397374
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1908  total reward: -11590.498811751731
timestep 1909  total reward: -11604.498811751731
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1910  total reward: -11606.334910711597
  Simulating cascading failure
  ok
timestep 1911  total reward: -11607.600205060939
  Simulating cascading failure
  ok
timestep 1912  total reward: -11608.606795292564
  Simulating cascading failure
  ok
timestep 1913  total reward: -11609.418515130325
  Simulating cascading failure
  ok
timestep 1914  total reward: -11610.578311655392
  Simulating cascading failure
  ok
timestep 1915  total reward: -11611.977655789226
  Simulating cascading failure
  ok
timestep 1916  total reward: -11613.785187229463
  Simulating cascading failure
  ok
timestep 1917  total reward: -11616.48831460267
  Simulating cascading failure
    depth 0: 1 overflowed lines
timestep 1918  total reward: -11630.48831460267
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
  Simulating cascading failure
  ok
timestep 1919  total reward: -11632.671715302322
  Simulating cascading failure
  ok
timestep 1920  total reward: -11635.466155585145
  Simulating cascading failure
  ok
timestep 1921  total reward: -11638.311672563428
  Simulating cascading failure
  ok
timestep 1922  total reward: -11640.817153604756
  Simulating cascading failure
  ok
timestep 1923  total reward: -11643.778282927338
  Simulating cascading failure
  ok
timestep 1924  total reward: -11646.612109313322
  Simulating cascading failure
  ok
timestep 1925  total reward: -11648.930507979212
timestep 1926  total reward: -11662.930507979212
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1927  total reward: -11665.17847252547
  Simulating cascading failure
  ok
timestep 1928  total reward: -11667.588584133733
  Simulating cascading failure
  ok
timestep 1929  total reward: -11670.286498696987
timestep 1930  total reward: -11684.286498696987
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1931  total reward: -11685.452653213395
  Simulating cascading failure
  ok
timestep 1932  total reward: -11686.760708578357
  Simulating cascading failure
  ok
timestep 1933  total reward: -11688.754478257746
  Simulating cascading failure
  ok
timestep 1934  total reward: -11690.568838793102
  Simulating cascading failure
  ok
timestep 1935  total reward: -11691.778460880594
  Simulating cascading failure
  ok
timestep 1936  total reward: -11692.615868317607
  Simulating cascading failure
  ok
timestep 1937  total reward: -11693.45991417957
  Simulating cascading failure
  ok
timestep 1938  total reward: -11694.490250550938
  Simulating cascading failure
  ok
timestep 1939  total reward: -11695.688251525207
timestep 1940  total reward: -11709.688251525207
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1941  total reward: -11710.625849886095
  Simulating cascading failure
  ok
timestep 1942  total reward: -11711.945859994838
  Simulating cascading failure
  ok
timestep 1943  total reward: -11714.030588005888
  Simulating cascading failure
  ok
timestep 1944  total reward: -11716.324706826457
  Simulating cascading failure
  ok
timestep 1945  total reward: -11719.499671661557
  Simulating cascading failure
  ok
timestep 1946  total reward: -11722.942453543808
  Simulating cascading failure
  ok
timestep 1947  total reward: -11726.502083960611
  Simulating cascading failure
  ok
timestep 1948  total reward: -11729.747199516103
  Simulating cascading failure
  ok
timestep 1949  total reward: -11733.052932101757
timestep 1950  total reward: -11747.052932101757
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1951  total reward: -11748.50351925692
  Simulating cascading failure
  ok
timestep 1952  total reward: -11750.270660123046
  Simulating cascading failure
  ok
timestep 1953  total reward: -11753.321291108094
  Simulating cascading failure
  ok
timestep 1954  total reward: -11756.490374713341
  Simulating cascading failure
  ok
timestep 1955  total reward: -11758.472373699198
  Simulating cascading failure
  ok
timestep 1956  total reward: -11760.354658938792
timestep 1957  total reward: -11774.354658938792
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1958  total reward: -11775.700887698868
  Simulating cascading failure
  ok
timestep 1959  total reward: -11776.675732209085
  Simulating cascading failure
  ok
timestep 1960  total reward: -11777.697862147592
  Simulating cascading failure
  ok
timestep 1961  total reward: -11778.50177040219
  Simulating cascading failure
  ok
timestep 1962  total reward: -11779.091706588097
  Simulating cascading failure
  ok
timestep 1963  total reward: -11779.760921414028
  Simulating cascading failure
  ok
timestep 1964  total reward: -11780.885969878509
  Simulating cascading failure
  ok
timestep 1965  total reward: -11782.422827818024
  Simulating cascading failure
  ok
timestep 1966  total reward: -11784.26061240384
  Simulating cascading failure
  ok
timestep 1967  total reward: -11786.181499331105
  Simulating cascading failure
  ok
timestep 1968  total reward: -11788.196612070844
  Simulating cascading failure
  ok
timestep 1969  total reward: -11790.66669716498
timestep 1970  total reward: -11804.66669716498
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1971  total reward: -11806.63570780529
  Simulating cascading failure
  ok
timestep 1972  total reward: -11808.441579461225
  Simulating cascading failure
  ok
timestep 1973  total reward: -11810.370225053362
  Simulating cascading failure
  ok
timestep 1974  total reward: -11812.273953331758
  Simulating cascading failure
  ok
timestep 1975  total reward: -11814.45132151697
  Simulating cascading failure
  ok
timestep 1976  total reward: -11816.714520599757
  Simulating cascading failure
  ok
timestep 1977  total reward: -11818.528235625507
timestep 1978  total reward: -11832.528235625507
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1979  total reward: -11834.09699318653
  Simulating cascading failure
  ok
timestep 1980  total reward: -11835.675371715408
  Simulating cascading failure
  ok
timestep 1981  total reward: -11837.233367679797
  Simulating cascading failure
  ok
timestep 1982  total reward: -11838.55240694477
  Simulating cascading failure
  ok
timestep 1983  total reward: -11839.692968147188
timestep 1984  total reward: -11853.692968147188
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1985  total reward: -11854.091592585966
  Simulating cascading failure
  ok
timestep 1986  total reward: -11854.65340387455
  Simulating cascading failure
  ok
timestep 1987  total reward: -11855.206229165527
  Simulating cascading failure
  ok
timestep 1988  total reward: -11856.078183462541
  Simulating cascading failure
  ok
timestep 1989  total reward: -11857.29076084812
timestep 1990  total reward: -11871.29076084812
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1991  total reward: -11872.264746979901
  Simulating cascading failure
  ok
timestep 1992  total reward: -11873.466606766953
  Simulating cascading failure
  ok
timestep 1993  total reward: -11874.579129631058
  Simulating cascading failure
  ok
timestep 1994  total reward: -11876.04731640124
timestep 1995  total reward: -11890.04731640124
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 1996  total reward: -11891.44276958175
  Simulating cascading failure
  ok
timestep 1997  total reward: -11892.660512128954
  Simulating cascading failure
  ok
timestep 1998  total reward: -11893.84834784138
timestep 1999  total reward: -11907.84834784138
Game over! info: The grid is not connexe
  Simulating cascading failure
  ok
timestep 2000  total reward: -11909.11993678876
In [38]:
#rewards_random_node_split = run_policy(random_node_splitting_policy)
In [39]:
rewards_greedy_switchoff = run_policy(treesearch_switched_off_policy)
Using chronics folder /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/chronics/14 and reference grid /home/marvin/Documents/pro/stagemaster_inria/PowerGrid-UI/input/reference_grid14.m
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3662215717864579, -1.2970515228101156, -1.1895290305956914, -1.0121149327923329, -0.8412235851697416, -0.9111810818665922, -0.9925113443433373, -0.8989285469562529, -0.9047377541831411, -0.9770230835287482, -0.9383482920587924, -0.9124687531855554, -0.9332396757468887, -14, -0.9609887343186105, -0.8829188359251471, -0.8918016836434738, -0.915602877932282, -0.8932029261641186, -0.9111286351189084, -0.8912277193642433] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0001  total reward: -1.9435697959292797
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9126406900398534, -1.7317192821653689, -1.7547388959127241, -1.2245377839347011, -1.1680133585507138, -1.2744970434021106, -1.3071182198660263, -1.1292147547797355, -1.1088924146213632, -1.1336245290388773, -1.1515713462320851, -1.1215287897241653, -1.1468448944349898, -14, -1.1667407091317454, -1.0956478651206107, -1.1030709982750164, -1.1289138909427265, -1.1061030091659922, -1.1272180315172717, -1.102346210759538] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0002  total reward: -3.7235589979857124
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.189899213014878, -1.1883486982019065, -0.9758875523195382, -0.7905353659792664, -0.7270931769314428, -0.7147405530574544, -0.8217166260273471, -0.6856079254201812, -0.6993747925910863, -0.7554119362559394, -14, -0.7008728499617777, -0.723992612715245, -14, -0.7423908872773625, -0.6886703674266025, -0.6827599546532033, -14, -0.6865355234481044, -0.7076167713393922, -0.684341336935822] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0003  total reward: -5.130316127346379
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1954442753670884, -1.2341711957575983, -1.1146277162440668, -0.8018426287270857, -0.7593469416556988, -0.8186578247512453, -0.8463622150945769, -0.7610228801538794, -0.7240926039064027, -14, -14, -0.7438934077672656, -0.7750779755863808, -14, -0.7813686162861729, -0.7339793293011816, -0.7255601695312381, -14, -0.7291411711570766, -14, -0.723997174707464] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0004  total reward: -6.549023315607579
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5283759161609005, -1.2047530062522236, -0.8261120229895772, -0.7033558767631887, -0.7325542619250195, -0.7311853026032558, -0.8512356198949537, -0.7174892274416655, -0.6977519568990215, -14, -14, -0.7128365326974575, -0.7390731761240389, -14, -0.7498658508827265, -0.704671254009862, -0.7008659125775164, -14, -0.6986871940294339, -14, -0.6947100135537357] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0005  total reward: -8.139803360869333
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.217368213177546, -1.7919738306166115, -1.160476430906479, -0.9936851711686329, -0.8921137730378016, -0.9138978231575687, -0.8635534427208256, -0.9278772819348798, -0.8974536569659239, -14, -14, -0.9193400621518518, -0.9534384078239211, -14, -0.9562805558010805, -0.8631035782056024, -0.8340047422607975, -14, -0.9013092166979066, -14, -0.896070031708019] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0006  total reward: -9.77721628517429
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3774029327458956, -1.4185846733419096, -1.0904085028326422, -0.9190765125936472, -0.8492780945972741, -0.8258907299542131, -0.9381002276493231, -0.8044036486772598, -0.8255664283652441, -0.922501521232483, -14, -0.8239275395080151, -0.8515082677748779, -14, -0.890606627749927, -0.8094067228583774, -0.8112373923883686, -14, -0.8062145081210882, -0.824913772449094, -0.8034081820441591] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0007  total reward: -11.675606278950761
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8528112371735994, -1.8600912275950425, -1.573448516663738, -1.2609870916244703, -1.1601210966309963, -1.1505344604037002, -1.3033813736453899, -1.1061924639330858, -1.118827123198382, -1.1912625327539166, -14, -1.1169873079818493, -1.1505241408299494, -14, -1.2088547540807042, -1.102067382308735, -1.086548006516734, -14, -1.0982760332621277, -1.1335185019134806, -1.0949818117323118] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0008  total reward: -13.96934383163354
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6038054346966246, -1.3769848658132349, -1.2581684162996414, -1.2316466443773642, -1.355513087029872, -1.2149680877328852, -1.2410137491162943, -14, -14, -1.2505055400576925, -1.315210372616677, -14, -1.3372279964436877, -1.2203489965502043, -1.2071710985541642, -14, -1.217340038787964, -14, -1.2071895461660433] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0009  total reward: -16.77706538110602
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3378636208072634, -1.8168142041515103, -1.692952583949351, -1.7121120805701584, -1.8788390333712313, -1.606463694432142, -1.6369222240208343, -1.7938278111759471, -14, -1.6311204331301559, -1.677128475575273, -14, -1.7511351985927195, -1.6116556928618908, -1.597120634538957, -14, -1.6053226626080042, -1.6405938270641407, -1.6005504509183182] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0010  total reward: -19.804677387065258
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9859677757097463, -1.6423761983513614, -1.4853112248037197, -1.4797700162074117, -1.5870567257803603, -1.4897667507566392, -1.43626547763241, -14, -14, -1.484090844851097, -1.5639648717654975, -14, -1.562493063775344, -1.4420535866713502, -1.4157272782000698, -14, -1.4429893199735555, -14, -1.4304913714202823] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0011  total reward: -22.679266430498796
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0499420603785365, -1.6659974740278254, -1.5407511652381876, -1.5227826114400147, -1.6912626256618948, -1.4608634668052873, -1.4943761608001387, -1.6874825380787337, -14, -1.490932078708665, -1.5317734996403474, -14, -1.5987639295586313, -1.4697939798938848, -1.480001103682764, -14, -1.4623086683854334, -1.4980661942551194, -1.4588617652334686] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0012  total reward: -25.463109351613824
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8365882824722988, -1.5125161637796218, -1.3979756963568495, -1.3761001373498465, -1.5393406954142446, -1.3389569356675721, -1.3563436495755465, -1.493634850074406, -14, -1.3576565586647247, -1.3970050989359306, -14, -1.4794198968449541, -1.3352884235620996, -1.3343210185974623, -14, -1.3278882307697992, -1.3621787503521758, -1.3249811558815605] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0013  total reward: -28.345051351482223
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2566357956858414, -1.7767824375861407, -1.6472665980985233, -1.653442250511779, -1.8422884009460219, -1.5840491536384416, -1.5852872635930095, -1.7044999489149346, -14, -1.5920526607002192, -1.635619035017461, -14, -1.721089062605713, -1.567985165493697, -1.5527390281912055, -14, -1.5597965070109678, -1.6041127956054062, -1.5569608439868388] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0014  total reward: -31.640758001959
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7331644156731856, -1.9077553227519233, -1.8274694119353672, -2.024543890904427, -2.038163476704865, -1.822324168904524, -1.7453540433860162, -14, -14, -1.7895479747777643, -1.8586985113095535, -14, -1.8854043689836075, -1.7664899114350452, -1.750519575226613, -14, -1.7537435312368528, -14, -1.7429676222855703] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0015  total reward: -34.943548548444554
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.840962905903801, -1.5871662750245392, -1.6458527052101386, -1.6279611665929463, -14, -1.6273738333469034, -1.5646892409991235, -14, -14, -1.601586363971979, -1.6578706636100142, -14, -1.7002297021203203, -1.5837755203586736, -1.5757256622914937, -14, -1.5676838302820257, -14, -1.5598229241999848] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0016  total reward: -37.511536772500826
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6744883789609524, -1.848024756162554, -1.3415920430377013, -1.1341045719242635, -1.0544800326645367, -1.0365002163879142, -1.148384061417884, -1.048123250886744, -1.0124216921752995, -14, -14, -1.0510301785175802, -1.1176702747800626, -14, -1.0991709736243103, -1.0198597856873253, -1.000294366945512, -14, -1.0190665322761956, -14, -1.0081652998562818] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0017  total reward: -39.623243016239975
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9358746161660594, -1.9653815909269363, -1.527641435213417, -1.3060945908167685, -1.183131665546009, -1.1340259125285306, -1.345168156980903, -1.0976437658237586, -1.1479727339090038, -1.2270035818431342, -14, -1.1407940914510517, -1.1813841644676377, -14, -1.2042237698023863, -1.1167790738336754, -1.1038306920071506, -14, -1.1151296240115305, -1.1686063001559308, -1.1114118767936407] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0018  total reward: -42.08449064692841
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9808697517378455, -1.553477073804062, -1.443007935306573, -1.4524288292161955, -1.6403531817147303, -1.3440612604574915, -1.3614335367964714, -1.4623670845888208, -14, -1.3915323348199984, -1.416513546087442, -14, -14, -1.3643359286402195, -1.4100931904897276, -14, -1.3658588754125174, -1.3833456572874419, -1.363603864864674] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0019  total reward: -44.763195219759794
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8363071087993454, -1.5218773220904087, -1.4113167704642895, -1.3819075580064442, -1.5594693512040554, -1.3445130332278918, -1.3646233717668224, -1.5093540624305373, -14, -1.3677120613141798, -1.4101868613558328, -14, -1.4734085043650045, -1.3448209192738088, -1.3430651201790513, -14, -1.338508577315501, -1.3632133573126823, -1.3346433123738937] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0020  total reward: -47.39788991416836
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8107701897577877, -1.6296454536393414, -1.3865737875740656, -1.304893247757076, -1.578346104243089, -1.2977381559682724, -1.3764542710771004, -1.5160143458881863, -14, -1.3348649112842914, -1.3849247254148447, -14, -1.2977381559682728, -1.3016646100634262, -1.2927785261035951, -14, -1.3060667907113919, -1.3727163870688026, -1.300051382034669] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0021  total reward: -49.82321531333544
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8863931247506804, -2.065924024765963, -1.5880979668276332, -1.2748179950452612, -1.1862131297400738, -1.191642450520917, -1.2986249030195849, -1.1609728021293553, -1.1421868009490783, -14, -14, -1.1719027413247132, -1.23328646389627, -14, -1.2279035550911426, -1.145822432385152, -1.1308764399862312, -14, -1.1426217705202562, -14, -1.13254687306348] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0022  total reward: -52.589690107593285
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.601115994722703, -1.8264021555599887, -1.735725011189464, -1.877250538456846, -1.9796471133126259, -1.6627680392142703, -1.64976244390015, -1.7281905865118754, -14, -1.6646441001137595, -1.7061930842796125, -14, -1.730200332223897, -1.6453235010368104, -1.623877339229101, -14, -1.6388213486639414, -1.6833103425237026, -1.6355983542716142] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0023  total reward: -55.69279968286986
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.741863049176177, -1.4871187614072934, -1.5567012624837537, -1.5592487873026, -14, -1.5365143321281733, -1.4828522150753798, -14, -14, -1.5183798019971353, -1.576318186772624, -14, -1.5951482253580809, -1.5004584425689422, -1.4884649179817488, -14, -1.4882311459270254, -14, -1.4792322360474752] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0024  total reward: -58.619413523747085
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.80523692990063, -1.5806239461214895, -1.4339123572834058, -1.4665984134252297, -1.3797368736467277, -1.509300894553099, -1.4524233278006082, -14, -14, -1.484009479140757, -1.5418954218399052, -14, -1.5795704595289892, -1.3953652201514353, -1.3443848662978308, -14, -1.4570106974301054, -14, -1.447381604829748] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0025  total reward: -60.75823378670925
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.353100643084383, -1.4096558235892147, -1.094812736348657, -0.9078902891726006, -0.8387400557810171, -0.8219405511767643, -0.9205865824663085, -0.794023862522413, -0.8167143083459053, -0.9101352444309608, -14, -0.8158284746060209, -0.8397493065605428, -14, -0.8784267483061519, -0.8001997306336701, -0.801014483354732, -14, -0.7960794770507479, -0.8141460547029582, -0.7944353966643316] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0026  total reward: -62.34981875223601
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3618470504647724, -1.3836688170983618, -1.1707076468831574, -0.9144468261628858, -0.8446847840499005, -0.8491034221418595, -0.953876426711896, -0.8016697458009218, -0.8113218122939085, -0.8742333476644327, -14, -0.8165357972684142, -0.8336823225930529, -14, -14, -0.7978303413214153, -0.8195807678344058, -14, -0.7998742444753071, -0.8146150639035571, -0.7975611030043507] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0027  total reward: -63.801704314512484
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.131348914014962, -1.1731965595354503, -0.9069457171521468, -0.7616301427368243, -0.6942640611690594, -0.6722662993624104, -0.7864281462013708, -0.6578340761398157, -0.6662367840143629, -0.7267295363484235, -14, -0.6690513136134416, -0.6811721377855737, -14, -14, -0.6544884929394369, -0.6688262596245685, -14, -0.6557202565633905, -0.66574469951862, -0.6543244592721195] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0028  total reward: -65.13252904724409
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1538592229796754, -1.1174843423690983, -0.9929012406482691, -0.7761419657150767, -0.7182407480569775, -0.7210180759659768, -0.8312058638165503, -0.6611883234837662, -0.67443139120176, -0.7072411237499048, -14, -0.6882970200724073, -0.7016516001506029, -14, -14, -0.678162745197295, -0.6891904945284757, -14, -0.6779015693917894, -0.6842485390086701, -0.6765002734594867] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0029  total reward: -66.64791525464119
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5431638386492605, -1.4748667998877318, -1.1815490698444122, -0.9625036065148896, -0.9076131456074772, -0.8935868152973316, -1.0262570600368888, -0.8517392501175383, -0.8766295151841341, -0.9436218453934324, -14, -0.875655619209498, -0.9039925720599183, -14, -0.9301080232479823, -0.858745909717682, -0.8505964274390858, -14, -0.8565589451249597, -0.8876804107816039, -0.8541978839133272] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0030  total reward: -68.45751151709936
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5619410541479577, -1.7708211270085932, -1.2832386949389334, -1.0931392779912157, -1.0018243432149456, -0.9815225994895704, -1.0901587951096396, -0.980337850417104, -0.9736238348283693, -14, -14, -0.9929418670878043, -1.050025299825473, -14, -1.0590471252555722, -0.970418647974857, -0.9581573424678513, -14, -0.9690945438196918, -14, -0.9589998350190863] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0031  total reward: -70.56013138209491
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9358589966630806, -2.081297367814258, -1.5620222319150014, -1.3235876208110395, -1.2074524116195406, -1.171893968295486, -1.3191186947849725, -1.141020395377303, -1.1770134842513278, -1.343962250940503, -14, -1.1718049020347485, -1.2056317172357487, -14, -1.2590967527214674, -1.1531570019092228, -1.1585949903295325, -14, -1.1474585948457605, -1.1665861560079975, -1.1444625225276943] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0032  total reward: -73.25458771470328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1467386499675656, -1.7734286361857052, -1.6458173638017002, -1.611156380194601, -1.8582915402299927, -1.5532653312176263, -1.5712133421897057, -1.7077871184151014, -14, -1.5885585922912193, -1.6185543759434988, -14, -14, -1.553857608500645, -1.5936284095285194, -14, -1.5569524754821753, -1.5758667177512429, -1.5534359372310844] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0033  total reward: -76.58497289256631
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4998597035260177, -2.0742465589062706, -1.8830006491113778, -1.8338528082662393, -2.100641605755066, -1.7946323447963157, -1.8098355967410857, -2.013865355509879, -14, -1.8184590399201987, -1.8647346940155074, -14, -1.9385929888053828, -1.7915319542134978, -1.7899208069589625, -14, -1.7794756518849801, -1.8234806308223241, -1.7771198466454112] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0034  total reward: -80.24616254706316
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7494381630652502, -2.1416797507590224, -1.993361632657288, -2.011733807291132, -2.2108716387412684, -1.8961038290291856, -1.9216456275962015, -2.119347692678394, -14, -1.9235107258817046, -1.9717198511728793, -14, -2.052833188951215, -1.8976956771390336, -1.887414018594339, -14, -1.8872448961243267, -1.929419361524477, -1.8840698078514408] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0035  total reward: -83.97807460292681
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.553851984172173, -2.1484707433712926, -1.9590748647772074, -1.8970775442881862, -2.184029914912023, -1.8462767185308908, -1.8930017711589886, -2.126408851134998, -14, -1.892725067777328, -1.9549456579649482, -14, -2.012810260337573, -1.8618787461431332, -1.8593105846929425, -14, -1.854340437544318, -1.88767254939155, -1.8478422480122] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0036  total reward: -87.51233584516072
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3592033032839907, -1.9329571832194692, -1.7827918634609583, -1.7580365199000167, -2.007697155400496, -1.6442791016442564, -1.6842576173672705, -1.8344848225656696, -14, -1.7166734527917558, -1.7394036501942438, -14, -14, -1.6842647137872344, -1.754372569547007, -14, -1.6891137234970803, -1.6949467896329482, -1.6879845237030244] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0037  total reward: -91.0626024453064
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7803319012972323, -2.109535218584304, -2.018009762854405, -2.0835473289180606, -2.265283656393059, -1.942501709742605, -1.9320719722929836, -2.080181364925132, -14, -1.9444333856650835, -1.9936742061294292, -14, -2.074124630467363, -1.9199700768000167, -1.9086834786961062, -14, -1.909246105521946, -1.9652767032118805, -1.9059874985014154] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0038  total reward: -94.5071778615129
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.172521752534817, -1.7304353066862115, -1.6301918525888273, -1.6268544874906083, -1.8121914944853315, -1.5532731533374067, -1.5650627353924829, -1.7319218393475753, -14, -1.57512354990529, -1.6124353174166715, -14, -1.6711866621558789, -1.550961727953753, -1.5393721721017148, -14, -1.5400292112690444, -1.5597506909007792, -1.5385879177050839] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0039  total reward: -97.41713007517491
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9496786803848412, -1.5526898607188502, -1.450496672883176, -1.448547845468767, -1.6055932732107974, -1.3732180743957507, -1.4047984310685073, -1.549101579595303, -14, -1.4035649369145273, -1.4449095126045608, -14, -1.501979519414887, -1.3811033302251638, -1.3768781088886215, -14, -1.3748934576311982, -1.4082740224997892, -1.371364295956925] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0040  total reward: -100.12345758082023
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8800467391006035, -1.5305122688559911, -1.4122662339507577, -1.3930232307886745, -1.5730974001998155, -1.3656609465919802, -1.3559383494555954, -1.4841830011776074, -14, -1.3626938542513094, -1.3992289277843697, -14, -1.4775609494551045, -1.3460815675226117, -1.3372693679406111, -14, -1.337793926446195, -1.364274369399453, -1.334963209688401] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0041  total reward: -103.13322820339036
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3293638134622454, -2.0762228410272643, -1.7964419406514862, -1.684786415225486, -2.0854684226694586, -1.6672282401130083, -1.770139274175948, -1.8907111684034636, -14, -1.7222259333442922, -1.7857013323891422, -14, -1.6672282401130079, -1.6732177172878955, -1.659713786756176, -14, -1.6809639922094757, -1.7728044815578092, -1.6748074128817336] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0042  total reward: -107.06474271280548
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9509393061610587, -2.5165375533307492, -2.261238648200724, -2.322161016030905, -2.1925915775075153, -2.3786718717592543, -2.273446795033731, -14, -14, -2.328561037006774, -2.4072812189820434, -14, -2.450757605254392, -2.192279115978248, -2.1216914176594415, -14, -2.283171567406772, -14, -2.271800722658949] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0043  total reward: -111.60038969557532
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.0102728390977584, -2.4400690414531834, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0044  total reward: -115.62305724460484
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.371520864903746, -1.6687805661023176, -1.62376417529324, -2.119921112978848, -1.5872110988004275, -1.612942407042046, -1.8287856018643467, -14, -1.6217858596781403, -1.6848339149840157, -14, -1.690350623247531, -1.5971754439110923, -1.55575959578544, -14, -1.5880364707029855, -1.6520623730416732, -1.582598507576332] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0045  total reward: -118.35421725773504
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9251303913852533, -1.5767418049321615, -1.4445754995449076, -1.4129471303862984, -1.639675347822466, -1.3686530711977418, -1.3897684605808727, -1.4784602656312418, -14, -1.3909350342457767, -1.4377917758337657, -14, -1.4909643301626774, -1.3674357327147713, -1.3486579107664387, -14, -1.3643764331198613, -1.4071654270438052, -1.3596391482264556] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0046  total reward: -121.10002955906296
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9715329096273055, -1.571684441053432, -1.4685264935721973, -1.4765138728394762, -1.6402721893553187, -1.420610669537966, -1.4197096601526675, -14, -14, -1.4413391153830453, -1.5045138941929899, -14, -1.5302630171860656, -1.4157424338221354, -1.405115106305917, -14, -1.4066014047650028, -14, -1.397154390561485] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0047  total reward: -123.80887159987235
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.818387614333364, -1.4587546832746814, -1.376160322200177, -1.3841176514191593, -1.5134307347005163, -1.3376738640096195, -1.3299694096931134, -14, -14, -1.352941713920487, -1.410724286833352, -14, -1.435252321263422, -1.3279092395088978, -1.316001029669902, -14, -1.3201294376921024, -14, -1.3116876502479025] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0048  total reward: -126.08309857890967
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5546909914361875, -1.7244178907464554, -1.3301314103629254, -1.0794318506660106, -1.0042744393426382, -1.0086929225925336, -1.0875020489160532, -0.9992971884399443, -0.9691102150247063, -14, -14, -1.0007877174530961, -1.0594758057835119, -14, -1.0598052577962345, -0.9733353907184898, -0.9576186789523347, -14, -0.972010286001776, -14, -0.9625393287894143] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0049  total reward: -128.35927035417382
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.231264300334727, -2.151464365987673, -2.0993034314183983, -1.485532853754046, -1.3953918882518155, -1.5000451517784337, -1.5695366334028045, -1.3424033105511246, -1.3332231004244905, -1.404588281079836, -14, -1.3421169740089873, -1.3771529795473731, -14, -1.4155491093551442, -1.3269501795325596, -1.3114089124988522, -14, -1.3217206736602665, -1.3556731547339336, -1.318553096311799] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0050  total reward: -130.41608381789032
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.237748893505724, -1.3710549736094773, -1.0333289943348962, -0.8368359234710138, -0.7794105878938464, -0.7809974966816937, -0.8449205912976486, -0.7706881696311911, -0.749751418384377, -14, -14, -0.7699013157321393, -0.8059080016212034, -14, -0.8114747290743543, -0.753546350941793, -0.7434795352804284, -14, -0.7509555422643307, -14, -0.7454045512176479] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0051  total reward: -131.85962271191255
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.206942158054476, -1.2491793198136902, -1.0150599454707059, -0.8000573231366706, -0.7404130448433198, -0.7413279405776839, -0.8149499740600239, -0.6937750079703228, -0.719701312504967, -0.8189823340582248, -14, -0.7146646229574557, -0.7333866291311033, -14, -0.754202343178603, -0.7049810493327662, -0.7043949051144401, -14, -0.7016384238335895, -0.7157172946807568, -0.7000593587417895] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0052  total reward: -133.25136011355428
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2378891838954167, -1.2208794203409559, -0.9656222880943068, -0.8072852798832948, -0.7432634026378617, -0.7193117284763278, -0.8590664995583263, -0.6936988862946432, -0.6983449032527942, -0.7438728060762078, -14, -0.7105042182468433, -0.7229579470653007, -14, -14, -0.6988554728526065, -0.7079276212770084, -14, -0.6992258771974638, -0.7133110426529353, -0.6979623936714202] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0053  total reward: -134.99517291946606
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9171586105867027, -1.7171140253831898, -1.6357158751908762, -1.1515515634684206, -1.1141709106730975, -1.2117723003419265, -1.27008200716504, -1.0648380620581812, -1.0596683932336404, -1.1151687248585542, -14, -1.0675006918349825, -1.0912357490543345, -14, -1.108366721574231, -1.0562250790285161, -1.0416403824698879, -14, -1.051631325295671, -1.0776262602233733, -1.0501139196171245] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0054  total reward: -137.2784228453443
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.871713085482521, -1.375749145923506, -1.3097809597687222, -1.383468585025161, -1.4999002260520147, -1.2827108985227058, -1.2460784952124089, -14, -14, -1.276745256201168, -1.33099626832815, -14, -1.335716273908863, -1.2592745817012447, -1.2505589733030091, -14, -1.2504216225440312, -14, -1.2416095434083445] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0055  total reward: -139.81520742881085
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7885437773015038, -1.4527319076885272, -1.363288138056316, -1.3568226234128895, -1.5311442593484506, -1.340513652516128, -1.3009256619927676, -14, -14, -1.3386914690600937, -1.4139009819712645, -14, -1.4033726379964042, -1.3135307704118349, -1.296892289679719, -14, -1.3088224101975745, -14, -1.2951750400582147] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0056  total reward: -142.61513588213634
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.101838039574268, -1.7050361473884026, -1.5788526209535358, -1.574606423448062, -1.7548451837363934, -1.5366334769786592, -1.5274208932449815, -14, -14, -1.5561044184395094, -1.632916138306564, -14, -1.6572145966129617, -1.5247821426064139, -1.510844953589239, -14, -1.516820670956804, -14, -1.5047534132673086] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0057  total reward: -145.82431810629572
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5059138184769223, -1.932136755498169, -1.7929742100486934, -1.8324645472318166, -2.030689699854021, -1.7567178454763595, -1.7206772439184457, -14, -14, -1.760104459612174, -1.8362959238881338, -14, -1.8736319728065316, -1.7277705529281313, -1.7175396718856308, -14, -1.7152645652779888, -14, -1.7044288108920587] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0058  total reward: -149.36558975355942
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6702372809026618, -2.068949219769806, -1.915544557162208, -1.969917132108489, -2.072772189799285, -1.9003118437545006, -1.8461899064260714, -14, -14, -1.9042897996527623, -2.015555721075787, -14, -1.9949690858923408, -1.8561801254862724, -1.8252626089355577, -14, -1.8561567688403664, -14, -1.8368428363716378] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0059  total reward: -153.08934000942986
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.632451863507314, -2.204624992788011, -2.00703700333317, -1.9523229248959189, -2.213270611347996, -1.9005485888265243, -1.9458917481053961, -2.240856167473046, -14, -1.937151277485235, -1.986867072799848, -14, -2.0833549252919528, -1.9136311156554728, -1.9125465200623302, -14, -1.9024780301534219, -1.9324767251773398, -1.898487646934876] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0060  total reward: -156.87558879661742
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6583207846379087, -2.192293478271265, -1.9989392390883063, -1.9535678023112992, -2.2194064158299285, -1.8956119128811664, -1.929328895587334, -2.149445181546293, -14, -1.929650753493562, -1.9819327466797543, -14, -2.063167033488191, -1.9018071629853435, -1.890245580313325, -14, -1.8916928252413951, -1.9249623144312717, -1.8877611402526961] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0061  total reward: -161.22844542808775
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.9739373803457387, -2.4968705284823525, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0062  total reward: -165.43712535967734
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.5294314481815157, -1.828102742578444, -1.7143907565542311, -2.295941907448858, -1.7161703085391395, -1.7414590713176323, -1.95962678825536, -14, -1.7503292260692451, -1.8109718017597323, -14, -1.8147956173267472, -1.7232205137392864, -1.6818588697274177, -14, -1.716448122139207, -1.7826776046944215, -1.7118094031072193] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0063  total reward: -168.41310025101268
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.03886020511387, -1.8081587485751827, -1.5526628701837175, -1.4564798269159591, -1.8130128054161667, -1.438544705793751, -1.5208226144674173, -1.5935100297368265, -14, -1.4894805453270128, -1.554476518490692, -14, -1.4385447057937522, -1.4461471680710647, -1.4327962548300215, -14, -1.4546589462822201, -1.5418401793944783, -1.446543443153815] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0064  total reward: -171.27075823579474
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9909741386167137, -1.5850250512973698, -1.4970504242950884, -1.5099663120544033, -1.6607495910918628, -1.4641758797426525, -1.4364244638740526, -14, -14, -1.4693444966693814, -1.5393434402023165, -14, -1.5493039964941304, -1.4433553603961775, -1.4284104263006294, -14, -1.4364552455546131, -14, -1.424861729952077] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0065  total reward: -173.9572006120702
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7447743538512686, -1.425246534760202, -1.320582666280016, -1.3157275284434689, -1.4459049252184484, -1.3065093454486645, -1.2687598895543664, -14, -14, -1.3096270555541016, -1.3753484918522452, -14, -1.3763213175470206, -1.2776861716794428, -1.2574836924432968, -14, -1.270922459470109, -14, -1.261580646323395] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0066  total reward: -176.83100020351804
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2694786144183845, -1.8439333267092441, -1.7165484141747298, -1.6893930142421882, -1.9381185359572735, -1.6263925935467127, -1.6496249296378938, -1.7642915147715907, -14, -1.6521676102073353, -1.7073278220072092, -14, -1.7617860231502598, -1.6269947348201854, -1.6111782830580794, -14, -1.6223360474196098, -1.6754588834837787, -1.6163158990045368] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0067  total reward: -180.19524184768278
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4495582898481363, -1.994154158310459, -1.8488750191627399, -1.8294097684286987, -2.0925838124045333, -1.7941931887698779, -1.767234315135409, -14, -14, -1.8100650078624545, -1.8972574052781646, -14, -1.8919577414026332, -1.7780290753726642, -1.7613168437638183, -14, -1.7670888803329854, -14, -1.7530633611066553] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0068  total reward: -183.3084408171576
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8767960318662489, -1.573477561245387, -1.4176363881314253, -1.3975500815347326, -1.5319925985061047, -1.3758778764686086, -1.3846135522300265, -14, -14, -1.4116188209137701, -1.488846408280848, -14, -1.4812820143901633, -1.3748123312954386, -1.3564668494601388, -14, -1.372304852102067, -14, -1.3601356083681504] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0069  total reward: -185.9235582028833
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7485214906690556, -1.4290608632400743, -1.3304804672837698, -1.3125909885576235, -1.4717545628335797, -1.2719859956033264, -1.287081069941188, -1.4158812661385032, -14, -1.28488616646324, -1.3202401867988975, -14, -1.3985133471897662, -1.2676125186382365, -1.2592841675305633, -14, -1.2616531293756452, -1.2902572228052043, -1.258650536265578] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0070  total reward: -188.61175546672783
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0551980108344914, -1.6108918021165721, -1.5166774480193181, -1.5252174380605374, -1.7076410364280317, -1.4513283541190434, -1.4504128293134373, -1.5712737457822348, -14, -1.459859201578508, -1.5007188974212364, -14, -1.5508637047363194, -1.4406395516898196, -1.429121761343471, -14, -1.4328944511869, -1.4647011761269642, -1.429546727578944] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0071  total reward: -191.52863297836564
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0991519486510453, -1.6397331771877819, -1.5551844428452304, -1.5958531441992374, -1.679317709565718, -1.5180101588429082, -1.5054409609030097, -14, -14, -1.5386238640530587, -1.620628957284333, -14, -1.6183238558637583, -1.5037746635154488, -1.4837710457904967, -14, -1.5016716921676918, -14, -1.4877557502943364] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0072  total reward: -194.11010734318535
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.882365798598578, -1.8608363019932734, -1.5584936948847607, -1.2365561669167804, -1.160274703714842, -1.1639628221079645, -1.289561928201617, -1.1126097550385907, -1.1198683098863307, -1.225622767897441, -14, -1.1235461112562894, -1.1566886862919372, -14, -1.2156616524703638, -1.1058800980496197, -1.104217444153811, -14, -1.1003724363587273, -1.1305999790604568, -1.097703319029236] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0073  total reward: -196.0546049210215
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4331999805165707, -1.5314413361122547, -1.1481365752848562, -0.9841382509896993, -0.8945540020752011, -0.8634750435467627, -0.983741452806352, -0.8430080487997179, -0.87229330866307, -0.9982643955589088, -14, -0.8660567905613866, -0.8897899895349806, -14, -0.932686214232606, -0.8534035640170086, -0.852372742031501, -14, -0.8486609735643855, -0.8648199238348132, -0.8467942588069164] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0074  total reward: -197.69455202532274
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.361914463487595, -1.4706055803416935, -1.0916954453747896, -0.9366778898201207, -0.8437594472874337, -0.8115122915035327, -0.9439246063103838, -0.8031541251261852, -0.8164060306098381, -0.9048708205954685, -14, -0.8143541229541216, -0.8277868896132753, -14, -14, -0.7969178977258633, -0.823921544953431, -14, -0.7985038466181172, -0.8117365918213136, -0.7969390555015023] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0075  total reward: -199.24577197935284
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2951285528292789, -1.4809497698638572, -1.0276139120349808, -0.9213496173451331, -0.8005854800939491, -0.7575977143690883, -0.8944718709399908, -0.7596209943013114, -0.8851171082161696, -0.8560135705143518, -0.8077413478888519, -0.775470568066644, -0.7965962968669109, -14, -14, -0.7553685208296113, -0.7544975904526401, -0.7836977532809919, -0.7588624156032907, -0.7889840140145822, -0.7543020563042468] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0076  total reward: -200.63843066222287
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1307263341247231, -1.1142145935654049, -0.8767009668465371, -0.7317644124036567, -0.6786846093423949, -0.6588589878073745, -0.768300206149417, -0.6408348029000976, -0.6416159061290304, -0.6854836534822771, -0.6595711293810002, -0.6529127503571406, -0.6613119925601886, -14, -14, -0.6382046898813721, -0.651460208327228, -0.6473077274177237, -0.6394114063814835, -0.6469696552280871, -0.6383566265657782] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0077  total reward: -202.07253764113207
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3446661585201467, -1.3032777903554447, -1.1496243992631148, -0.9063614496711987, -0.8431127499625254, -0.8460381854144905, -0.9689749978588957, -0.7785581380297324, -0.7933748871974853, -0.8374666440755997, -14, -0.811342236821734, -0.8255471520152028, -14, -14, -0.7972709849426924, -0.8120729814433235, -14, -0.7970006775210257, -0.8052183931728062, -0.7959022890278188] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0078  total reward: -203.72173509087273
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.510152569853464, -1.5125579830862186, -1.2252584920514098, -0.9772352966652715, -0.9197246634709286, -0.9205399270166374, -1.0126182251430076, -0.8736753794926304, -0.8917668912685156, -0.9970849491671323, -14, -0.8907572255916156, -0.9156174047164088, -14, -0.9587583734034373, -0.8770313046706306, -0.8783761487627827, -14, -0.872601744174104, -0.8923749227091519, -0.8706393117109286] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0079  total reward: -207.49731407926154
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.9666453937589625, -14, -2.912481022905093, -3.053525009682622, -4.062800865180903, -14, -2.9311980057132785, -2.9620214087926233, -14, -2.912481022905094, -2.9175975410311517, -2.914952439341577, -14, -2.9064626608379, -2.922840213337884, -2.9049396766778774] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0080  total reward: -211.7958580090626
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9105807749235253, -1.611291594842526, -1.465847587171586, -1.4306454115665845, -1.5973433400406518, -1.3997634380613488, -1.43408206384654, -1.6269649546399856, -14, -1.4281718749349033, -1.4718549314584752, -14, -1.5679647265166439, -1.4046879838584132, -1.4093593447987152, -14, -1.397673631950862, -1.4206121340195759, -1.3936042531231974] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0081  total reward: -214.92232184043326
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.475902561147747, -1.9428246801320517, -1.835990526335504, -1.8486949813550388, -2.04564049725061, -1.735903519848795, -1.7709603704302634, -1.9312842849095353, -14, -1.7710230544977699, -1.8261078414663754, -14, -1.8819897997689699, -1.7440197917900642, -1.737215407046895, -14, -1.738611399117155, -1.7838964305833276, -1.7328595782474387] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0082  total reward: -218.47419161023467
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5094159098737436, -2.1113249317494462, -1.9288312146632465, -1.8679264816603496, -2.15287557884185, -1.8248508258133511, -1.8600637652540222, -2.082070750109756, -14, -1.8580301682588092, -1.9129345854481494, -14, -1.986980548076909, -1.8334781858286318, -1.821381782324097, -14, -1.824339522468391, -1.8556257162439158, -1.8190101915539818] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0083  total reward: -222.1288491776149
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.625982656836149, -2.1022141788212845, -1.9418723163844593, -1.9295116691457455, -2.149971976555348, -1.851336204667888, -1.8713149692381978, -2.090488624392838, -14, -1.8798715702448445, -1.9267365303189732, -14, -2.0073093660395873, -1.8495231728453145, -1.8464948948149693, -14, -1.8378672603444894, -1.8698091948775244, -1.8356473758262526] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0084  total reward: -226.25934022504703
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.042704587110346, -2.6295753989567774, -2.3667422818129396, -2.331160581754922, -2.4259068936048873, -2.302309587250231, -2.3570115800904508, -3.442217036843994, -14, -2.3146874316050448, -2.3272796254236816, -14, -2.574480262876153, -2.3006559336993373, -2.45300838558741, -14, -2.2941604849644937, -2.289473475868117, -2.294843671605874] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0085  total reward: -230.3322328592757
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5489391655408213, -2.0770803655574874, -1.9037218388861168, -1.8594735414850598, -14, -1.7630307236636378, -1.8824022830692702, -14, -14, -1.8055280849720123, -1.8182497431793614, -14, -2.014535721860994, -1.7771984078739738, -14, -14, -1.7834033155763562, -1.7185040681586414, -1.7834191583605723] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0086  total reward: -233.51027689777584
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0824810746705587, -1.6672028867639415, -1.5427864977564811, -1.5334639858908952, -1.6920960892843748, -1.4476007284707713, -1.5022686097404958, -1.6920346209343538, -14, -1.4883954014671534, -1.5252179697367072, -14, -1.5839103936799517, -1.469443380277867, -1.4589907220894849, -14, -1.4624770394452142, -1.4874148564840166, -1.4595399703415048] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0087  total reward: -236.2730086856055
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8329445740528891, -1.5338967229850582, -1.3930462970530595, -1.3534839065719992, -1.5788080738884982, -1.3144535904009205, -1.329016264719921, -1.4403398737106523, -14, -1.3454882210666297, -1.369337227668706, -14, -14, -1.3147804882777474, -1.3486211995843436, -14, -1.3174258734557005, -1.3389552307490664, -1.3151310593588812] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0088  total reward: -238.69487425634884
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.827838053344301, -1.9338236595670963, -1.589618460496952, -1.3041014772865052, -1.171929376163412, -1.1471908681173568, -1.3081277858355793, -1.109198792138716, -1.1343335883510726, -1.2358920970873877, -14, -1.1370841704601138, -1.1748947003382821, -14, -1.2126099628266191, -1.1158638879458254, -1.1098845619668887, -14, -1.1107086886258493, -1.1413095038003547, -1.107411980342382] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0089  total reward: -241.0717893982003
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7103709469127912, -1.477681951040612, -1.3410452534803297, -1.291836453897, -1.4835621924925526, -1.272722363238977, -1.3067128398894374, -1.4440403649821822, -14, -1.3036322768364204, -1.3481809445885833, -14, -1.4202911884317235, -1.278285817570814, -1.278627298248464, -14, -1.273710600670613, -1.31059507339213, -1.2695031615090775] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0090  total reward: -244.23151894609464
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.219554196346571, -1.9195381450170688, -14, -1.9758983235823298, -14, -1.969710898157721, -1.904565663427698, -2.0156517365331776, -14, -1.9258441251211857, -1.9754306450070842, -14, -2.072449055383141, -1.9060698402882825, -1.8897476932621324, -14, -1.8941629280370351, -1.9328043041132434, -1.8902263863852378] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0091  total reward: -247.83761542558108
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.364246756959719, -1.9223954734365551, -1.8011919195343133, -1.7972972635613733, -1.9936336519192193, -1.7465503156604212, -1.7445612369536476, -14, -14, -1.7777208204351171, -1.865138106251624, -14, -1.8848304187021798, -1.7385641588470988, -1.7219659778588121, -14, -1.7293655910438521, -14, -1.7163487862243108] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0092  total reward: -251.03727394303294
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1714482729413973, -1.66623707265089, -1.5577602100270551, -1.6003171788644763, -1.7283880562604927, -1.5102018276208784, -1.5000990645169918, -14, -14, -1.5276387923069803, -1.5917364074187528, -14, -1.6033546831642973, -1.501879975392648, -1.4893678689066034, -14, -1.493015324487591, -14, -1.483309731227564] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0093  total reward: -253.74358732475045
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7210164797529834, -1.380511431906267, -1.2796917635630392, -1.2868367200272783, -1.3988117673796592, -1.2583551501651473, -1.2328451754400396, -14, -14, -1.2673200248784098, -1.3312313273631389, -14, -1.3325156359000836, -1.237617361360443, -1.2211902739651872, -14, -1.2326529508889412, -14, -1.2230036504899324] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0094  total reward: -256.33422541795466
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.944615933238167, -1.5377226846418808, -1.445447758938957, -1.4551726629570865, -1.5931690561076042, -1.401577086718835, -1.3912825647685592, -1.5394003323469554, -14, -1.3973433618327162, -1.428234433264897, -14, -1.520380949830013, -1.3803212482381881, -1.3770025858389126, -14, -1.3707869485470692, -1.3975585535953146, -1.369447819239016] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0095  total reward: -259.1001114270313
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9921236228438302, -1.5788999698128974, -1.4785197123640932, -1.4792031938192485, -1.6435182853744765, -1.4141341449993243, -1.4198722268462742, -1.5642308511824152, -14, -1.4255820156995207, -1.4593713350170887, -14, -1.522647012397729, -1.4074790337063856, -1.4009512880872417, -14, -1.398235181330427, -1.4287936132085044, -1.3964381898376368] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0096  total reward: -261.5310787611246
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8136506054022794, -1.7847595833105667, -1.455397090413288, -1.1758533656402577, -1.0972359777904788, -1.0847820883515618, -1.2314166315774577, -1.0389244787818388, -1.0585480444418651, -1.1448422010675552, -14, -1.0564836766989718, -1.0854100738485828, -14, -1.1338081559146502, -1.0412384780199373, -1.0291082891808756, -14, -1.036634619628004, -1.0697449720069665, -1.034529144255688] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0097  total reward: -262.9774018889929
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.43126281573320535, -0.4266469724850292, -0.52311545916591, -0.4711735650005103, -0.4115890655226156, -0.42118770800766747, -0.41799984561731574, -0.5531576206856587, -0.4155359414456208, -14, -14, -0.444960961314382, -0.488937812904264, -14, -0.5530023749728172, -0.4199476794920625, -0.4137190306175548, -14, -0.42455170629852923, -14, -0.4172148386874165] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0098  total reward: -264.0351252504055
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9537760190899209, -0.9564323223387254, -0.8977542507671357, -0.7405655634411273, -0.6166697931680154, -0.6683678282611659, -0.7385363183491579, -0.661296920098573, -0.6518877958850517, -14, -14, -0.6700102602222924, -0.7033450632033013, -14, -0.6995023419694091, -0.6588022005019382, -0.6540051952809532, -14, -0.6509865047226151, -14, -0.646134295889948] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0099  total reward: -265.2269387836988
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9578687755775198, -1.0613652359333083, -0.7435900882064794, -0.6319790172826647, -0.5988237585774765, -0.5914379246109637, -0.6332602370146286, -0.5947720489603346, -0.5805336626461421, -14, -14, -0.5965023385684155, -0.6307520563179191, -14, -0.6356262927310372, -0.5801705244445743, -0.5700029191844171, -14, -0.5809250561203414, -14, -0.5751437401253037] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0100  total reward: -266.3552393137022
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9631174117748409, -1.0074669585272908, -0.7657522555130551, -0.6345140670169518, -0.5892028254779603, -0.577900472226954, -0.6423981119721952, -0.5558537333618101, -0.5747125576120784, -0.6523275850172255, -14, -0.5708947549662509, -0.5852779967490557, -14, -0.6137518983682528, -0.562305739451309, -0.5624574625037314, -14, -0.5592543629519433, -0.5699526595649107, -0.5582976108189557] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0101  total reward: -267.71823301175436
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3995746165030813, -1.4812730522578046, -1.1039359535657, -0.944060625647854, -0.8560155177291128, -0.8231851242506963, -0.9635911531950841, -0.8149699199088251, -0.8295691824015718, -0.9223583683674235, -14, -0.8216157327768037, -0.8361449328605162, -14, -14, -0.8069725844537626, -0.8244571925102152, -14, -0.8094715851007313, -0.819913970497127, -0.8071399646903511] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0102  total reward: -269.33680010764465
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3959723740976553, -1.4039644664004054, -1.1016349100297147, -0.9436059547742295, -0.8622023150151754, -0.82869544060648, -0.9790123573579955, -0.8157468073280546, -0.8190792727947107, -0.850162158865241, -0.8502913175358994, -0.8320792296694671, -0.847640797489368, -14, -14, -0.8111770733131196, -0.82229223856132, -0.8304171415912952, -0.8141343797780808, -0.8277463151739856, -0.8115945114365201] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0103  total reward: -271.0961665554367
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5952615253923577, -1.6855318296095845, -1.2811017690420916, -1.1149957531095744, -1.0043571937928009, -0.96215947023197, -1.1372996242961342, -0.9520861832608293, -0.9663327986099971, -1.0366589953866334, -14, -0.9709665712906314, -0.9894387307183312, -14, -14, -0.9484180156005184, -0.9719575995316344, -14, -0.9502765588894198, -0.9730121186048649, -0.9481893744789377] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0104  total reward: -273.55213337300114
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1664681881080092, -1.7350115472201393, -1.595815834411619, -1.5846118282295512, -1.8013690402442957, -1.498829738992831, -1.5131639664732797, -1.6431016011648623, -14, -1.535886909145533, -1.5627629699282093, -14, -14, -1.508633468419081, -1.5629590388959569, -14, -1.5108689530462462, -1.539205601670054, -1.5077774430855393] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0105  total reward: -277.17148375411
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.361057381086415, -2.2458593639374005, -14, -14, -2.2059439161127643, -2.1308683429279154, -2.174806074077312, -14, -2.15654724387561, -2.2147129682173645, -14, -2.2729139951810264, -2.1327627592364697, -2.097898864296712, -14, -2.1259025628001087, -2.190660719271855, -2.120520642116014] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0106  total reward: -280.5985187169626
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7623935574166825, -1.5046409706084076, -1.3646887841814925, -1.3591116326113464, -1.4028344358720068, -1.3933294038328305, -1.3322019088134431, -14, -14, -1.3908064983100887, -1.4868864140385198, -14, -1.4525392932419383, -1.327040391413796, -1.2859463433617937, -14, -1.3448875147566934, -14, -1.3291360985558767] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0107  total reward: -283.64519918016293
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5591159158775363, -2.0032741641192153, -1.862423180337509, -1.8765735364045932, -2.0797285051305274, -1.7749408985854898, -1.7996032816369811, -1.9524464114686089, -14, -1.802394054837591, -1.8615241078286675, -14, -1.9404665578767848, -1.77332025166729, -1.7614776917450328, -14, -1.7667142422374162, -1.8131397979462165, -1.760734119838535] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0108  total reward: -287.0495796092363
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.354488136171126, -1.862814632389897, -1.738560865930223, -1.7415011656487436, -1.9238287125711049, -1.6577961382742286, -1.6765627256037314, -1.8608553713262195, -14, -1.6751519755665047, -1.718845281715015, -14, -1.8013140806619488, -1.65595746428698, -1.642390807472696, -14, -1.6475864025455642, -1.6703453837463758, -1.643646309234791] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0109  total reward: -290.0636034584642
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9351772975353603, -1.5726557271096835, -1.441993389968635, -1.431086353650225, -1.617256338535222, -1.3996591171045671, -1.389553935798028, -14, -14, -1.4180518469270031, -1.484725207396304, -14, -1.498308287217745, -1.3899880306905057, -1.379197774190609, -14, -1.3816542613897118, -14, -1.3716330417551934] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0110  total reward: -292.63953641140154
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.639518516913285, -1.3482076416785127, -1.2618969549678234, -1.2543824294934132, -1.3865907288164745, -1.2441899874833133, -1.2142177572214221, -14, -14, -1.2498864106647383, -1.3186195985213172, -14, -1.3226765809110719, -1.2193016907232062, -1.2044055699266945, -14, -1.215189703466554, -14, -1.204299911182162] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0111  total reward: -295.17751579895975
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8049324469093975, -1.6243941730169908, -1.4287742763559805, -1.3397850192153498, -1.7495744092550778, -1.33770941457765, -1.3981475243940515, -14, -14, -1.374521057670302, -1.4463645258621647, -14, -1.33770941457765, -1.343337487382103, -1.3479080495580082, -14, -1.346930954385955, -14, -1.3336794763760196] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0112  total reward: -297.58945429010765
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.826091082862162, -1.9394315302892993, -1.5125934385355484, -1.2033549534033687, -1.1314618944512371, -1.142257174420217, -1.2494378996826063, -1.1182283698225237, -1.083303380007218, -14, -14, -1.1163466797165746, -1.1728339849206877, -14, -1.1735109006015825, -1.0923924762707382, -1.078382786682357, -14, -1.0870522810627423, -14, -1.0782590147719813] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0113  total reward: -299.82298426274593
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8121175547776798, -2.1559222782434992, -1.5450266445853063, -1.3133228799016967, -1.1978203561902763, -1.1830434095377718, -1.2662864917396832, -1.195276098460861, -1.1631026467680177, -14, -14, -1.2007647370992718, -1.2690030417189668, -14, -1.2643568153129954, -1.1621695936985217, -1.139562604944817, -14, -1.1660228956336778, -14, -1.1552709578663067] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0114  total reward: -302.52755782967915
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.188342108856336, -1.784325746930754, -1.657351030526576, -1.6329588341507066, -1.8480310134429798, -1.5778648754367381, -1.599806350842589, -1.7301968994894112, -14, -1.6006935334884151, -1.6507664729650589, -14, -1.725782499230496, -1.5743974691369593, -1.5693988801566552, -14, -1.569761067068479, -1.6240935029691026, -1.5650109619883865] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0115  total reward: -305.7148310758738
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2749254723061436, -1.8520871230263123, -1.7169030139719301, -1.6921024192604015, -1.897834240366735, -1.6307479443730901, -1.656320500007388, -1.8463813073662785, -14, -1.6586787676619525, -1.7006955672956552, -14, -1.7712179157413805, -1.6344296362312243, -1.6308611130455235, -14, -1.6248379313983738, -1.6570503997816524, -1.6222622842062386] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0116  total reward: -308.5965351974601
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.824237150446846, -1.4296605766426336, -1.3306013652976052, -1.3402722632974517, -1.4642928797422592, -1.2648623252261966, -1.286107722557137, -1.4299718092382392, -14, -1.2866597607926527, -1.321505972554728, -14, -1.3736697255352277, -1.2687771627554012, -1.2686493877050762, -14, -1.2623828606328389, -1.2869653581686784, -1.259441837380071] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0117  total reward: -311.0876564392856
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.69735589199517, -1.5206788831691123, -1.3256109275595827, -1.2382938147824754, -1.5636841450747192, -1.2232302044688448, -1.2974314370379691, -1.353023929989046, -14, -1.2691632843492646, -1.322638636809272, -14, -1.2232302044688455, -1.228711130985925, -1.2184591314362803, -14, -1.2373897172244148, -1.332317419213627, -1.2316794044453645] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0118  total reward: -313.5371383116571
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7442175396762845, -1.4196829317350292, -1.2995164969483064, -1.2820301062673147, -1.4803160312890502, -1.24722632005518, -1.2459297444416848, -14, -14, -1.2725067587570875, -1.335262838636973, -14, -1.3206097584315402, -1.247899975665545, -1.2382504488251067, -14, -1.2410005980880385, -14, -1.231022740935229] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0119  total reward: -316.0253067794311
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7366118613990558, -1.4079931185718948, -1.3148584363742675, -1.3167684248128795, -1.4238736663558977, -1.2880669874926263, -1.2676965137875607, -14, -14, -1.3006225879890592, -1.3706357577651016, -14, -1.3611407546377634, -1.2709918670465634, -1.251345629676314, -14, -1.2690138114048477, -14, -1.2571457268387753] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0120  total reward: -318.074910610431
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4044850123401877, -1.351528551235691, -1.1813489471720224, -0.9031126105909653, -0.8474234097049747, -0.8629648676625132, -0.9581670356939642, -0.808137112325506, -0.8098624884177501, -0.8689756494511017, -14, -0.8148879073730365, -0.8373984099586465, -14, -0.8603578811004251, -0.8037229563402453, -0.7958751298236688, -14, -0.8000296284507381, -0.821361381927332, -0.7982582013236826] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0121  total reward: -319.4490591429813
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9489573001654157, -1.0969995104852774, -0.7716405929838924, -0.6472421797526319, -0.6014191315336563, -0.5958997751759504, -0.634235635751013, -0.5909017838560506, -0.5832820513650109, -14, -14, -0.5998829541506053, -0.6346520283253946, -14, -0.6235957198178229, -0.58186370890487, -0.5704378432504722, -14, -0.5841621330761996, -14, -0.5782734027266144] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0122  total reward: -320.5964291094414
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2716576205007821, -0.943928437527747, -0.6811675727407767, -0.5890246480851045, -0.608977144639707, -0.6019146091887567, -0.7091540074832521, -0.5912509700793243, -0.5836376897494241, -0.597463697784173, -14, -0.5895096131491421, -0.6095270227289913, -14, -0.62674219995704, -0.5798371345378215, -0.5723399411038598, -14, -0.5791101729378717, -0.6011235952584043, -0.5769321232095902] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0123  total reward: -321.5977787005413
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.722784577688006, -0.7800728438331339, -0.57795359226832, -0.4825583646751708, -0.449973065927334, -0.4434655033356168, -0.49660447153493287, -0.4399182332692998, -0.43436706991695645, -14, -14, -0.4444979006254424, -0.46805205552154544, -14, -0.4722137217272153, -0.4346692319020386, -0.42952396818383715, -14, -0.43277548619223266, -14, -0.4290096499960843] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0124  total reward: -322.4388955194096
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.708461465890824, -0.7234103253376012, -0.5843516542289303, -0.4561351873369131, -0.43335752181904014, -0.4424248826908902, -0.4857370832685474, -0.4185737863663248, -0.4199166882516037, -14, -14, -0.4247491474351605, -0.44418573599537753, -14, -0.45429792949037434, -0.4172515953987591, -0.41514708899527, -14, -0.41525033462658734, -14, -0.4121071688721705] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0125  total reward: -323.30325414464835
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7477420304998609, -0.8146247066192377, -0.646164684584218, -0.4961874650724804, -0.47154561005798346, -0.49047636296789454, -0.5028181061587069, -0.4674608369774662, -0.4543768080621346, -14, -14, -0.4691730186351682, -0.49391939137596375, -14, -0.48956284795048943, -0.4563379548262561, -0.44873410349481, -14, -0.45604545683999703, -14, -0.4522514563666009] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0126  total reward: -324.3107749446816
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9648465157401482, -0.9655987173642415, -0.7710054553269113, -0.6275815710070328, -0.590082058371994, -0.5849894015867381, -0.6503654822460319, -0.5714643768033387, -0.567886956691671, -0.6240926100389413, -14, -0.5715845960592129, -0.5875518608290885, -14, -0.6209423012188828, -0.5632994821019836, -0.564798914394117, -14, -0.5600522462283299, -0.5710073353925575, -0.5587866965384278] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0127  total reward: -326.08653999155786
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8717806038382476, -1.34442566592347, -1.2903197932514165, -1.378183826031292, -1.4483612980978229, -1.222282092310368, -1.2339334010128695, -1.3486202318947356, -14, -1.2373056252073769, -1.2646790788393802, -14, -1.2886069440298449, -1.2248568601404566, -1.2136883770486375, -14, -1.2189347106406179, -1.241642924683239, -1.2169783503378377] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0128  total reward: -328.28887340489416
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6735826184480265, -1.8074105997089756, -1.3702415349340602, -1.1279067656845323, -1.0401502381077519, -1.0261747225289386, -1.1664577191481802, -1.01564434831569, -0.9966740108001938, -14, -14, -1.0231624562933492, -1.0728614068522468, -14, -1.0744828134569915, -1.0025034656535032, -0.9917663898117424, -14, -0.9961350667646555, -14, -0.9886450362877205] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0129  total reward: -330.4178677865935
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8705746621830885, -2.0976369464683327, -1.6018359115357645, -1.2978477357168754, -1.1931750765704177, -1.192018415303259, -1.3042714907976345, -1.1757612030568025, -1.1463164967907775, -14, -14, -1.180423777103371, -1.2471987861479554, -14, -1.2322984808493822, -1.1540636986962955, -1.1346788565951305, -14, -1.1520532948895426, -14, -1.1403493454115738] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0130  total reward: -332.6248599745452
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8316050709080194, -1.889978047663836, -1.4359241458579977, -1.2341529226849577, -1.134168041980075, -1.0940405291934376, -1.257663742325598, -1.0752209510979918, -1.1023872248979925, -1.230825618972568, -14, -1.0993763738477071, -1.132797271401448, -14, -1.1940412363011814, -1.0800879308458224, -1.0823792178976248, -14, -1.0748765271292182, -1.1100059782531708, -1.0723133313565372] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0131  total reward: -334.7876358104677
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8301260291749746, -1.9426243762289965, -1.4971827228581613, -1.2646366681973098, -1.1515190146189214, -1.1182274525419225, -1.2677232304524098, -1.097981822440384, -1.117260853638956, -1.2652187753524842, -14, -1.1127838786194528, -1.1397173563779963, -14, -1.2116176135690029, -1.0990303388021094, -1.0931249291419938, -14, -1.0921782071955846, -1.1109976573078217, -1.0904625045659797] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0132  total reward: -337.05877820675846
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0494904989839355, -1.9994309574856484, -1.7158992323431232, -1.3492358592984472, -1.2535016061301805, -1.2542438772176476, -1.4197867267848139, -1.2001925496361783, -1.1990685889739008, -1.2777907333739702, -14, -1.2027745895391864, -1.238231502301351, -14, -1.287376574587802, -1.1889143932849742, -1.1710295297575128, -14, -1.184421551607921, -1.2108470509231852, -1.1806798917248205] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0133  total reward: -339.42434826116255
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.734935850425664, -1.3325376015236132, -1.256054516172131, -1.2902970735525403, -1.3981002385039354, -1.2317177087480073, -1.2012556602967766, -14, -14, -1.2249563492973583, -1.2675274474933722, -14, -1.293248070824443, -1.210783132252935, -1.1997796267194867, -14, -1.2007548238487817, -14, -1.194540524646515] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0134  total reward: -341.6432234331912
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7727513441322, -1.7978993171590567, -1.5149512207724427, -1.155359355981744, -1.0823142117830384, -1.109306611754707, -1.2478304661593431, -1.0572050380842803, -1.0286069981048156, -14, -14, -1.0541012092439894, -1.096545429555643, -14, -1.1033165499155337, -1.0395807601521114, -1.032770798751306, -14, -1.0306623417028373, -14, -1.0243346473821948] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0135  total reward: -343.41638953362224
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2793292755345822, -1.3872800232062286, -1.0353713848613004, -0.8572537531607695, -0.7885636298480472, -0.7746758151020803, -0.8852738017603312, -0.7630831352468346, -0.7567867077678946, -14, -14, -0.7755674502505956, -0.8147658812232856, -14, -0.8089242461688656, -0.75895009415495, -0.7514761626019244, -14, -0.7548578306918136, -14, -0.7488314530488038] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0136  total reward: -344.90723156528463
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.192168440674155, -1.3963359716728627, -0.9634052031330609, -0.8446034458042467, -0.7717041154743021, -0.7518092761664644, -0.8232083730482398, -0.754129783142192, -0.7558212642565957, -14, -14, -0.7713037557077708, -0.815274413563687, -14, -0.8182559139505484, -0.7489380781893404, -0.7375348557411615, -14, -0.7489442376116328, -14, -0.7420105786136116] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0137  total reward: -346.6549814785359
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5442673938291778, -1.9601407935422384, -1.2708434933930661, -1.1557278667726676, -1.0389174624399737, -1.0125887857007738, -1.0591199065931907, -1.0103007373675927, -1.0437077154032444, -1.5514066510671307, -14, -1.0201243896701093, -1.026807730754946, -14, -1.1490265016513292, -1.0122697195689394, -1.083867469441613, -14, -1.0100561823960987, -1.0081449092088293, -1.0102150575100546] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0138  total reward: -349.0223791418956
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.3971756192255147, -2.113220233735895, -2.1424699206446145, -1.5361558900197614, -1.4474931713488335, -1.5364737107880588, -1.8608770668708814, -1.3751943822179018, -1.3925840302621673, -14, -14, -1.372385022608784, -1.3814861278251087, -14, -1.5101401927995335, -1.3569386627770919, -14, -14, -1.3595256668866644, -1.321155741981873, -1.3592527541509225] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0139  total reward: -352.3823971079249
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9617082213239585, -2.3044649587158315, -2.1232215186157934, -2.17488629991475, -2.218052021450283, -2.0605074511847707, -2.0783390055794992, -2.801195736551463, -14, -2.0532250174025397, -2.0668793755197163, -14, -2.2554347694940637, -2.0526183118911043, -2.0959616135792913, -14, -2.038754500343861, -2.031710874490094, -2.0388622240473775] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0140  total reward: -355.26037458439987
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.462928263733587, -1.5054041975331964, -1.136563123478215, -1.0099299878115988, -0.9018432229811243, -0.8539088665538751, -1.1034720672984046, -0.8332714474816956, -0.8960603280954984, -14, -14, -0.858269815172204, -0.8656790721662756, -14, -0.9487208804340465, -0.8514779112815806, -14, -14, -0.8463454565811683, -0.8244612728715317, -0.8462666019849158] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0141  total reward: -356.8124641099771
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2541402400306538, -1.2966409308684355, -1.0097405591535495, -0.8367072617333952, -0.7701489200547271, -0.7524158236748018, -0.8524934881947739, -0.7252670912651761, -0.7477398144171971, -0.8396318194402421, -14, -0.7434659530161712, -0.7654068579369523, -14, -0.7966417481051469, -0.7327816185939661, -0.7315732671203072, -14, -0.7297531297716333, -0.7478056767301816, -0.7276282527056712] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0142  total reward: -358.36077730446186
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4443343538382443, -1.4873513113850871, -1.1289960735975126, -0.9578747652448049, -0.8745336003930126, -0.8423532001972148, -0.9942727777765533, -0.8297276508430527, -0.8414257092092783, -0.9162685071902841, -14, -0.8396245053376811, -0.8574849495454616, -14, -14, -0.8233367984094978, -0.8420069744615543, -14, -0.8259860501969707, -0.8418284231166049, -0.8230461032196087] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0143  total reward: -359.89386731151683
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2330930257799386, -1.2609890291394394, -0.965438261389053, -0.8280718308094782, -0.7544288144202963, -0.7242080317176396, -0.8625642380287396, -0.7127142038774152, -0.7205230430542733, -0.775985535895962, -14, -0.7262080002991804, -0.7408579388499468, -14, -14, -0.7102550715374109, -0.7261481486516261, -14, -0.711845454922021, -0.727805933231574, -0.7100439038353704] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0144  total reward: -361.1186041371939
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9005619538600257, -0.9048721351171408, -0.7068563708273858, -0.5967177898681534, -0.5472034847673248, -0.5282767846017974, -0.627955522040614, -0.5144095874161242, -0.5185874887516675, -0.5566412303194569, -14, -0.5266808652991136, -0.5371031009325239, -14, -14, -0.5149950034211427, -0.5261850358462422, -14, -0.5157869311636337, -0.5260721217669064, -0.5146929218417722] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0145  total reward: -362.0359660610355
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6775654593303085, -0.6999984354325355, -0.5675009915518838, -0.47003411430009207, -0.4269029468251409, -0.41635046668546555, -0.47824954304421907, -0.40913326606419975, -0.4103182457507183, -0.4426551944283497, -14, -0.41250112762404906, -0.4253557288536203, -14, -0.4439257910105919, -0.4058943994595001, -0.40361789443054447, -14, -0.4040706818390837, -0.4159332805716562, -0.40295233642542694] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0146  total reward: -362.8109994133887
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6331722087000748, -0.6599268424909673, -0.5121575246563674, -0.4301486606250714, -0.3935948953669004, -0.3825384306427106, -0.4359087793979117, -0.3741810438874321, -0.38085966559420475, -0.4249155401393815, -14, -0.38013852204107085, -0.39037552169760054, -14, -0.4104326045810731, -0.374972543968868, -0.37362790496491477, -14, -0.37285357186520823, -0.38178432198109635, -0.3720810159277416] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0147  total reward: -363.3515091111142
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.17236762484341245, -0.1711718854279215, -0.2123001926080586, -0.19395640173570433, -0.16690707589672985, -0.16902771524831145, -0.16874099449082688, -0.21188567048015433, -0.1685849899127143, -0.17122612106696733, -14, -0.1767977128946067, -0.18640700645942507, -14, -0.2340736915765217, -0.16919468770109772, -0.17155113821682644, -14, -0.16963514389901535, -0.17662585223438926, -0.16842868179780662] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0148  total reward: -363.79817358293053
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4144930885980421, -0.40396202062083686, -0.37851155545121784, -0.321775920783965, -0.2651002314510222, -0.2854132909628893, -0.31547382852838507, -0.2866194876133995, -0.2839486724162772, -0.31792779694760426, -14, -0.28685638665034097, -0.29683483230944996, -14, -0.30744610922245275, -0.2825300583436758, -0.2781919109830215, -14, -0.28059477748169026, -0.28714189512645655, -0.2797573959196177] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0149  total reward: -364.46565815391784
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7172795392003054, -0.7366207303965949, -0.5774202089480995, -0.49611385646137296, -0.43272906065686995, -0.4085117815499878, -0.5093319397053346, -0.39961543412759337, -0.42409819708756097, -0.4378620706907444, -14, -0.41310489568888864, -0.4303886707795124, -14, -0.3996154341275932, -0.4005243418650061, -0.3990431676039679, -14, -0.4045479761069517, -0.43178458563085026, -0.4023843395362575] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0150  total reward: -365.5259678598126
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1463795179834402, -1.1139936891583377, -1.0158270379196477, -0.7331145498074437, -0.698263937215258, -0.746521192608442, -0.8111991312989775, -0.6851644140404941, -0.6638388055115763, -14, -14, -0.6775832139585396, -0.7028852785669567, -14, -0.7158407676704983, -0.670473907115059, -0.6679375783580854, -14, -0.6653946679336308, -14, -0.6612665382908168] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0151  total reward: -366.8148132249321
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0270381896300056, -1.1473934675840034, -0.8741048327405687, -0.7099658022056854, -0.6560172392749569, -0.6559943123203175, -0.7139862873930255, -0.6402607945049256, -0.6370184804540512, -14, -14, -0.6473218213589403, -0.6773880815656601, -14, -0.689760190817934, -0.6348866150703399, -0.6283309740053882, -14, -0.6323928099034711, -14, -0.6275788268286694] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0152  total reward: -368.1772583746597
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2456942391606716, -1.3301417233871882, -1.0216526192384745, -0.8279366202216418, -0.7721492878251598, -0.7698567635749471, -0.8594384391120579, -0.7545051179223022, -0.7420005945435925, -14, -14, -0.7601567193309966, -0.7938895451525171, -14, -0.8026969117888973, -0.7447724543258083, -0.7374492026019717, -14, -0.7395194397133642, -14, -0.7348663228989267] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0153  total reward: -369.7505953540052
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4162264896236945, -1.4742327501583463, -1.1843655597554732, -0.9560463808320099, -0.8843977711326678, -0.8792989210569544, -1.0158106016925719, -0.8623025460509903, -0.8466168345143747, -14, -14, -0.8678565836931503, -0.9155772326176607, -14, -0.9186820866726522, -0.850782583335583, -0.8450864574364374, -14, -0.8466274457317187, -14, -0.8384706564465756] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0154  total reward: -371.3798613621436
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2920262070002644, -1.4234249112759492, -1.0989953622358886, -0.8692020428800895, -0.8232630991525879, -0.8428958265827727, -0.8744625177634134, -0.8210324148885351, -0.7958451608431176, -14, -14, -0.8199685212681121, -0.863805865611132, -14, -0.8690867046202337, -0.7983669862146873, -0.7848862805039379, -14, -0.7977158518144748, -14, -0.7907953516918129] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0155  total reward: -373.05565970885164
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5221090078351096, -1.5737205168123252, -1.2742712211759193, -1.0156090195069198, -0.9411745481617093, -0.938975202163275, -1.0345788373619296, -0.8977195810807121, -0.9079781897653624, -1.028941336110512, -14, -0.9100982736816825, -0.9328753043445197, -14, -0.9723345133295526, -0.898235885479522, -0.8977640483887738, -14, -0.8925454068474468, -0.9017323839061574, -0.8909120662040885] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0156  total reward: -374.877268166754
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5992206584764377, -1.572375470575428, -1.3570817054380402, -1.053720059460921, -0.9853082177017423, -0.9972984851108077, -1.1025958808668743, -0.9368881402784447, -0.9508599869492491, -1.0282986295887915, -14, -0.9507660512015006, -0.9810107519892701, -14, -1.0201848831527212, -0.9364038258292041, -0.9319139079087791, -14, -0.9338979419765876, -0.965637458145783, -0.9306963916983318] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0157  total reward: -376.5781200931071
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3520651173573144, -1.3459187164184616, -1.0719075809249374, -0.8741988886269901, -0.8161791811660613, -0.8038696405621947, -0.9103668937273166, -0.775972748548439, -0.7852667999274506, -0.8629526064446341, -14, -0.7900032681814336, -0.8140849763752239, -14, -0.8404571222986448, -0.7761976972112518, -0.7761365522219283, -14, -0.7720151859337696, -0.7904249700742317, -0.7701555346547491] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0158  total reward: -378.4156695897012
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8768704407799874, -1.6654079002367812, -1.6915303715199783, -1.1640937676833019, -1.1283156429690777, -1.2588450108735147, -1.2855000551810767, -1.105997859163691, -1.0733035686230423, -1.1087692466124561, -14, -1.0850818898988461, -1.1095382634379543, -14, -1.1442108080350102, -1.0742351731861908, -1.0575565716772295, -14, -1.0689411617921782, -1.0944808325906017, -1.0673939619394044] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0159  total reward: -380.0552551226168
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9682641130086839, -1.0763688014996782, -0.7893103897682794, -0.6598061104118825, -0.6094048246068439, -0.6003918383953359, -0.6665010742174987, -0.597466395622328, -0.5867985739206706, -14, -14, -0.6053401663193386, -0.6383626222828157, -14, -0.631867345483396, -0.5887268808215764, -0.5801032269539014, -14, -0.5869158556218506, -14, -0.5820289612383569] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0160  total reward: -381.2974734843167
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1633644651842103, -1.1490768195576733, -0.9403386986722485, -0.7501057387242154, -0.701882224036936, -0.6988384078671231, -0.7843648082526289, -0.674048095202312, -0.6715194509636107, -0.7335296267414286, -14, -0.6754566594097506, -0.692758324018041, -14, -0.7215871709214163, -0.6674398145300711, -0.6614053199525647, -14, -0.6634023521937069, -0.673351423610445, -0.6621151347459103] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0161  total reward: -382.57940858968453
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0316499154553695, -1.1293750932713764, -0.8247662317486334, -0.6927364354819779, -0.6486089136661576, -0.6403838312203606, -0.7036191132491825, -0.6422806325996094, -0.62572334202607, -14, -14, -0.6458366484309491, -0.6868560051616601, -14, -0.68412233607524, -0.6278959034046653, -0.6178535361994513, -14, -0.627528128764499, -14, -0.6205297854153028] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0162  total reward: -383.99660486343805
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3934683671119776, -1.389370786227927, -1.1132814864815375, -0.899911683940856, -0.8453112132684636, -0.8390946938689852, -0.9351978534365561, -0.809382424039366, -0.8146903284976643, -0.8934405360683523, -14, -0.8172887474947096, -0.8393270341670127, -14, -0.8807030394960242, -0.8056722338794398, -0.8007370681554011, -14, -0.8009554746670446, -0.8152643890159972, -0.7993427375540473] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0163  total reward: -385.57621865990154
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3490634634526528, -1.385282793566775, -1.0356918787532747, -0.9033552597591631, -0.8270734064719044, -0.7919268005221624, -0.9238546852874967, -0.7859851359175166, -0.798939450549648, -0.8765467926109762, -14, -0.7980765585630515, -0.8219853434261041, -14, -0.8644321883211777, -0.7863684530904606, -0.778558288351479, -14, -0.782324725089414, -0.8005214223277946, -0.7802710589094677] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0164  total reward: -387.08165692222224
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1753518724083418, -1.3151351358781773, -1.0369320020217252, -0.8131286553577167, -0.757780612366333, -0.7751702332614996, -0.8140190868637279, -0.7534019066744965, -0.7307025598541481, -14, -14, -0.751450599562299, -0.7911929262736189, -14, -0.7925355542228686, -0.7345472479710174, -0.7225606382717813, -14, -0.7336463426697554, -14, -0.7268799739692108] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0165  total reward: -388.40858548098424
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0273308473972567, -1.0577885533331128, -0.8429852058872328, -0.696851885237772, -0.6395468079885183, -0.6256920479810594, -0.710857482475842, -0.6005666980191166, -0.6236885965685485, -0.6825419352309254, -14, -0.6202910900202048, -0.6412032192000873, -14, -0.6659901680785584, -0.6080680821128321, -0.6063205675103265, -14, -0.6062896180084493, -0.6287115785152205, -0.6043679204901932] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0166  total reward: -389.69260396680454
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.239474337912619, -1.2262365204687313, -0.9223206746772343, -0.7807674794790396, -0.7270739504172727, -0.7014439037669006, -0.8295300691977476, -0.6837498396032489, -0.6889342687437389, -0.7620138061746822, -14, -0.6966035677747007, -0.7070984973995309, -14, -14, -0.6836566967264011, -0.697838685148069, -14, -0.6843538325907786, -0.692283939562294, -0.683451787801171] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0167  total reward: -391.04814156126326
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1707445487777917, -1.1435577782495718, -0.9416944266500181, -0.7726149343143357, -0.7143780215580311, -0.6990787111023093, -0.8256751566904008, -0.6656238184955987, -0.6719319933506822, -0.7127503500999823, -14, -0.6862917577289164, -0.7005190933940973, -14, -14, -0.6729823693779147, -0.6809413225112497, -14, -0.673685505710527, -0.6814992536532583, -0.672085806657543] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0168  total reward: -392.7799554964241
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8504308199143584, -1.8480080355084791, -1.5267034693860715, -1.216359573158404, -1.13007291191649, -1.1245886694911762, -1.2630699524132791, -1.0615685530129313, -1.095818335478339, -1.1949422327789476, -14, -1.0896634570746027, -1.120259245308195, -14, -1.1632410159823046, -1.0726308320355478, -1.0616247690451053, -14, -1.0685119751684031, -1.1031672527012721, -1.0661901166652759] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0169  total reward: -394.48516939405954
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.101400202398903, -1.1606514966209593, -0.8610495673116773, -0.7519112250257342, -0.681868362388387, -0.6525563380763569, -0.7683981643493905, -0.6453497464374468, -0.654119529250898, -0.7088137511914937, -14, -0.6572523856642001, -0.6691508306975531, -14, -14, -0.6436643292405294, -0.6593527218245394, -14, -0.6451225852794014, -0.6561490032075612, -0.6436453446225147] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0170  total reward: -395.9828360881561
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3184229762744863, -1.6585910553903835, -1.083830647697865, -0.9744752327294203, -0.879661608306882, -0.8582408086437365, -0.899417486955739, -0.8540488125667579, -0.8764628368752332, -1.2376528830443663, -14, -0.8609404030540192, -0.8618673676747562, -14, -14, -0.8421917941917354, -0.95817227167286, -14, -0.854003681950459, -0.8569221223296731, -0.8540213494740291] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0171  total reward: -397.36698480153257
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9342769018866938, -0.9579705103835168, -0.7282422045633573, -0.6325081047259017, -0.5754988130033959, -0.550520679131384, -0.6488977158490579, -0.5450011379270475, -0.5466699367364912, -0.5851369502145026, -0.5601684870882166, -0.5557223736508297, -0.564790093358994, -14, -14, -0.5421209911791396, -0.5554252348168324, -0.5509290058826097, -0.5434382008372233, -0.5488566081958979, -0.541956919184682] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0172  total reward: -398.51591470906084
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0731986034639238, -1.0111309042974426, -0.8858260930977688, -0.6844174875084573, -0.6448122947897179, -0.6531890307270884, -0.73444431370758, -0.6008026957915193, -0.6039168795845422, -0.6339151894951706, -0.623547632728909, -0.6194234752085979, -0.6295441747262115, -14, -14, -0.6059172390824301, -0.6209905795388405, -0.6134943306039484, -0.6087921358795719, -0.6123134744586117, -0.606972988343605] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0173  total reward: -399.824997616573
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2448552925129028, -1.2332233619313862, -0.9997245108023095, -0.811987546056532, -0.7523359779425395, -0.7392470199270363, -0.8289295912217126, -0.7019655468476084, -0.7248667194610249, -0.7775753554627606, -0.7400814479422411, -0.7239534768251743, -0.7392365720058808, -14, -0.7656770893403977, -0.7043168213305694, -0.7096153123251351, -0.724708466978633, -0.7098821758588724, -0.7226958185083178, -0.7082802117206822] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0174  total reward: -401.3554006099457
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4678232460798453, -1.426318275816674, -1.1628829926781508, -0.9443872711903765, -0.8806441889946375, -0.8662405943491644, -0.9986017810069392, -0.828705974240119, -0.8297377315517062, -0.8800431263902321, -0.8557745396048257, -0.845223012683205, -0.8577861329629753, -14, -14, -0.827994790172524, -0.8413745372430675, -0.8403452664592116, -0.8305568771465262, -0.8369100672519207, -0.8284374465251223] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0175  total reward: -403.3133093664599
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9633848516944488, -1.8853601148809696, -1.662781510217179, -1.2855689599383906, -1.1999189685622236, -1.2132201099840099, -1.385296989514542, -1.1188742979641773, -1.128020648718224, -1.1817471211506927, -14, -1.1505789349739148, -1.174633135402912, -14, -14, -1.131575919205506, -1.1468025215307984, -14, -1.1330207589010846, -1.1560432558627038, -1.1299139663416367] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0176  total reward: -405.75285833125497
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8939299116391626, -1.514240045512971, -1.397747187794051, -1.3892920031688805, -1.55427894819134, -1.3224228530310616, -1.3548672014064518, -1.476373937197249, -14, -1.3511183631783832, -1.390542329669356, -14, -1.4534042356209809, -1.3279711431142196, -1.3160795301251424, -14, -1.3238618091630054, -1.3568537944959487, -1.3206746668308404] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0177  total reward: -408.40991926613594
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9067395898861397, -1.5084965090595575, -1.4049804772540864, -1.4224073269789146, -1.5459763598272849, -1.3747924469749384, -1.3553992793367033, -14, -14, -1.3848465838903894, -1.4490150027158883, -14, -1.4663445736200629, -1.3578526851015056, -1.3435587357157117, -14, -1.3508226392158433, -14, -1.3409814047558508] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0178  total reward: -411.3196826314849
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.106394137110892, -1.7433181537762295, -1.630245518266184, -1.6289948047450915, -1.7184180466088472, -1.6153887049683218, -1.5836323506554537, -14, -14, -1.6269679859926174, -1.718599740592381, -14, -1.7211450339105168, -1.58025430986751, -1.5537250982135595, -14, -1.5839700300007047, -14, -1.5687819605931128] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0179  total reward: -414.36578490998966
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0313876460665456, -1.7070614803760507, -1.5822020813452489, -1.5355329179646642, -1.759940189031896, -1.4974533968362762, -1.5262331970148049, -1.7042915085708346, -14, -1.5201988185369686, -1.5557511525015784, -14, -1.6305924305609283, -1.5039388076428815, -1.4933911687424488, -14, -1.494650201681705, -1.534236756654635, -1.4923771802912222] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0180  total reward: -417.46514558694906
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3000949312547414, -1.812289117007389, -1.7016298174804683, -1.7087416138283371, -1.8951092673208663, -1.6252499227895583, -1.6344932378662465, -1.7834768387720168, -14, -1.6398659412953789, -1.687262651938014, -14, -1.7499089252374769, -1.6195268146283492, -1.6148651195817925, -14, -1.611674514130609, -1.6509797138456612, -1.6069834966681549] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0181  total reward: -420.3087494899402
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.691251577208061, -1.425528647968089, -1.3054353071577027, -1.2700398731023486, -1.4359779702894937, -1.2427187230497303, -1.2671931152270892, -1.4191042221258672, -14, -1.2674817358721717, -1.3023422283939732, -14, -1.368930907709332, -1.246501830642103, -1.2510086857327307, -14, -1.2388372162532244, -1.2701562122122199, -1.2366204063230208] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0182  total reward: -423.6458783645094
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.703635052831022, -14, -2.1782718201582467, -2.0941500902680485, -2.292163482743366, -2.1222940804746915, -2.2379764276711023, -3.2527384349040287, -14, -2.1206322075646815, -2.1432492585535083, -14, -2.1222940804746924, -2.107588618280148, -2.153687034571683, -14, -2.1023382550187857, -2.103732877079926, -2.1005084682460846] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0183  total reward: -427.06016485492273
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.4967733822253149, -1.3868051803575394, -1.2728299924666966, -1.510519594030151, -1.3092881572329802, -1.3601048977442498, -1.4915321109815696, -14, -1.347626816917062, -1.3869183236700509, -14, -1.438331534363468, -1.3274308501280965, -1.325985207350434, -14, -1.3246872059174615, -1.3520906886774802, -1.3201364001453062] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0184  total reward: -429.4679050755402
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9572255348535679, -1.9860500221971635, -1.5938253079863942, -1.2990514973743472, -1.2017989475561466, -1.183320841739572, -1.3371444148548814, -1.140745041557097, -1.1607849618202821, -1.284270830010669, -14, -1.1607255037327298, -1.1915421092407568, -14, -1.2464719470348495, -1.143529785001469, -1.132506739492899, -14, -1.1368989971619914, -1.1574724490639867, -1.1349102281508112] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0185  total reward: -431.77745804403867
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.635638005098282, -1.3039861034478708, -1.2318881487024365, -1.2464079580979943, -1.3347924707212402, -1.2208367087575225, -1.180902110649075, -14, -14, -1.2194908249958347, -1.28355576205906, -14, -1.2722282043038207, -1.1900077104444697, -1.170814932567221, -14, -1.1872079880614148, -14, -1.1770462290055475] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0186  total reward: -434.79983330236485
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4678311443300416, -2.1757110071583403, -1.9112521484400398, -1.8671745241064166, -1.9748527949287904, -1.840097848953229, -1.9084556165430928, -2.8100882109652274, -14, -1.8690225147202426, -1.8835452775943042, -14, -2.038351723425411, -1.8567899983063947, -1.9773821390043211, -14, -1.8517112450132527, -1.84744546073918, -1.8515603257589464] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0187  total reward: -437.94165396803214
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.825705423565595, -1.4991543612937128, -1.3774121075408212, -1.3522486635301278, -1.5521990815833175, -1.2889906488163747, -1.3036738064910331, -1.426346891664458, -14, -1.3268714911576593, -1.3459647915650403, -14, -14, -1.3011828611629408, -1.3374703127423522, -14, -1.3030580012559132, -1.3137688980953535, -1.3017228167140416] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0188  total reward: -440.7721578921679
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8588088104100062, -1.5629603609285703, -1.6207721365069423, -1.6462383436763244, -14, -1.601788093955475, -1.5548818391587838, -1.5807125162991549, -14, -1.5757785843930385, -1.6290720166481658, -14, -1.6886870674206778, -1.549270982782784, -1.5274997169269042, -14, -1.5471498784125353, -1.5935352713782682, -1.5415132753194123] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0189  total reward: -443.8562749107789
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0124756331869227, -1.6906373761350193, -1.559535291152904, -1.6038242555315747, -1.49992189112196, -1.6032575591140918, -1.560937179045408, -14, -14, -1.5987418001725495, -1.6599652637411468, -14, -1.6592165082402073, -1.5066041616241228, -1.4523680546008344, -14, -1.5659403293011032, -14, -1.556617301684061] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0190  total reward: -445.92825926512813
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6315215423608735, -0.6251153444360266, -0.7988681165898344, -0.7214771491968331, -0.6161640765573903, -0.6222832549682313, -0.6236516167871843, -0.8005431319270326, -0.6182694853701604, -0.6411924225698672, -14, -0.6466951723526595, -0.6769374825868688, -14, -0.8375294981424779, -0.6225327263387053, -0.6224529429338014, -14, -0.6226832834790729, -0.6508040086810245, -0.6196162997484251] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0191  total reward: -447.71681394662085
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7636346783987693, -1.6851410929494932, -1.6456354037445706, -1.3459334403592957, -1.1065498062699262, -1.2135417340829584, -1.330808811657541, -1.1827629130553727, -1.193991711559591, -1.3013850141187853, -14, -1.198927812033321, -1.2403599329427677, -14, -1.2672851445520459, -1.181307861488208, -1.156323003753444, -14, -1.1762570855287995, -1.2149527206173523, -1.172390604935319] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0192  total reward: -450.02552987280427
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0307841853540247, -2.0021433918532723, -1.7596826740895068, -1.3853068393949395, -1.2751407045095364, -1.2748452142131903, -1.4467883263598127, -1.219916594881725, -1.2242799226106174, -1.2862360354680176, -14, -1.2305405763485857, -1.27454273102716, -14, -1.3209623165591728, -1.2087755109981007, -1.1954995036653382, -14, -1.2069882223422896, -1.2518358290257747, -1.2021661199135247] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0193  total reward: -452.13301151055646
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5002993941708505, -1.7132151646922542, -1.235027647893933, -1.0365864775422866, -0.9523596353102786, -0.9383898120042696, -1.0282791995740606, -0.9350804625182583, -0.9188943555538632, -14, -14, -0.9457784932231683, -0.9978652750460719, -14, -0.9856020387317143, -0.9212592746968912, -0.9050472310328169, -14, -0.9204265119652623, -14, -0.9119821340868467] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0194  total reward: -454.1313985512459
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.312547251867834, -1.1088784651057793, -1.1519804806046756, -1.1616540535056934, -1.3430671179849765, -1.1380103833578912, -1.0997421906414082, -1.1378209480231438, -14, -1.1139341547110169, -1.1411422348379063, -14, -1.182010798854276, -1.1009879893234475, -1.083365039422493, -14, -1.0949988119075935, -1.1172697835184189, -1.0933398096566433] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0195  total reward: -455.86192794694466
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0492939714305785, -1.2149289254220335, -0.8874260493749907, -0.7460271216885626, -0.676001230542817, -0.6645941722922628, -0.7353756708801892, -0.6651636305719458, -0.6512305845026366, -14, -14, -0.6723015350814401, -0.7084612486379696, -14, -0.6987457099969353, -0.6539485139568849, -0.6432442854249663, -14, -0.6526083349343779, -14, -0.6471643562762489] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0196  total reward: -457.0900314614565
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0075272659608479, -1.071024976715369, -0.7923620942226781, -0.6744482763415907, -0.6180223995549816, -0.5979738516232708, -0.6770931399393374, -0.5815257801673988, -0.6017992380552533, -0.6851834674208053, -14, -0.599852066886282, -0.6178029012205987, -14, -0.6393557674645949, -0.5891034938717078, -0.5929160900169187, -14, -0.5863941876404916, -0.5973931129008501, -0.5848592290868363] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0197  total reward: -458.3255958705089
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0722556714523659, -1.1686865085920841, -0.9044462311035446, -0.7752854948450304, -0.6909691561564659, -0.6662737955683748, -0.7751986494769327, -0.6553629717062914, -0.664429568760294, -0.7398953889638349, -14, -0.6676966514658231, -0.6800791887790946, -14, -14, -0.6532240257264612, -0.6795130296418476, -14, -0.6557179575240027, -0.6645011234288858, -0.6540386288850134] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0198  total reward: -460.0350808349335
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8348801673238206, -1.774488075023621, -1.5270542777008573, -1.19745410511718, -1.12051294135612, -1.1257870360534434, -1.2664619509807047, -1.0499486464851524, -1.0541439106389061, -1.1165871035676007, -1.0851834291342661, -1.0756782772148925, -1.0902915389642946, -14, -14, -1.0552179976793428, -1.0783730017594484, -1.0676881253362176, -1.0586485294554968, -1.068075431258937, -1.0562609386981492] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0199  total reward: -462.53759246851826
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7409987516619005, -1.467334724588312, -1.5265121943140436, -1.5519558586448894, -14, -1.5108557701437417, -1.4596877106998638, -1.470924773151161, -1.5259233499348468, -1.483585497402114, -1.5179867297572642, -14, -1.5600074037153968, -1.4445567098753165, -1.4543808426759093, -1.4888875569357247, -1.456679637495454, -1.489795737501952, -1.4525629870996424] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0200  total reward: -465.52923245841737
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.195752766016695, -1.7893946162583685, -1.6376938108521104, -1.6099472211659827, -1.8152063391325415, -1.5548384558100006, -1.5779902966766197, -1.7688998242898508, -14, -1.5791556869827488, -1.623017667836501, -14, -1.6816094200107385, -1.5595435802153346, -1.5581845088620838, -14, -1.551172378542733, -1.5791154170850887, -1.5470832800237455] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0201  total reward: -468.69734003420376
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.302983774132694, -1.8701912338508913, -1.7197242329745657, -1.6915793775590597, -1.9335093585168683, -1.6235096787978072, -1.6601133652188569, -1.7825463485068693, -14, -1.660350767418753, -1.7124165667449556, -14, -1.7710623496062632, -1.6307842291684056, -1.6180202426847536, -14, -1.625291676914848, -1.6897544967793539, -1.6210242957626513] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0202  total reward: -472.1287057238002
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5694975641057964, -2.062027868600016, -1.9067162696522277, -1.9048738228735234, -2.126919995821668, -1.856471014615259, -1.8284317117332034, -14, -14, -1.871750147487188, -1.9653692395700064, -14, -1.959918159741523, -1.8373065668812678, -1.818802194411657, -14, -1.8291421593669772, -14, -1.8133454469116523] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0203  total reward: -476.13282584606213
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1392288921539238, -2.6884579036226435, -2.350955487186016, -2.2269481325527916, -14, -2.1977137179144512, -2.3017804791224683, -14, -14, -2.2574495836778583, -2.3494802479585815, -14, -2.1977137179144512, -2.1994498615429814, -2.2135068443395256, -14, -2.2039949023057788, -14, -2.1907746753503115] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0204  total reward: -480.4182529098994
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9995254733797205, -2.35641509442491, -2.1962805367148013, -2.22973178901764, -2.4209665831693385, -2.1497238883340124, -2.110995757658767, -14, -14, -2.162873083837459, -2.278331403786919, -14, -2.2695956131100656, -2.120892686965519, -2.094810819312904, -14, -2.1151932439278487, -14, -2.094652388487004] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0205  total reward: -485.0310871995836
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2179849320375458, -2.7793544840154802, -2.525567463482232, -2.561448095517691, -2.447267758312116, -2.611725251243458, -2.525004851710525, -14, -14, -2.5779514355530067, -2.672918215573984, -14, -2.7131276712145054, -2.4573999340426544, -2.3764085174988296, -14, -2.534065075366783, -14, -2.5181819011971913] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0206  total reward: -488.919573927222
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1634299873893315, -1.748581368650998, -1.600809354964304, -1.5807647005398595, -1.7876425854628262, -1.517778041429437, -1.5501901155625135, -1.6804455581339868, -14, -1.549710626575967, -1.5936926059894774, -14, -1.6687390058173648, -1.520931085090641, -1.5068114101199315, -14, -1.514688716079296, -1.5613662426517265, -1.5120782101395291] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0207  total reward: -491.85570982098966
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0664938979701284, -1.6139076706884852, -1.49473987093605, -1.5269250503412564, -1.6472167433795275, -1.4997768942397611, -1.4344283769672574, -14, -14, -1.4774890900567383, -1.5523895065087223, -14, -1.575936298269085, -1.4485546903757929, -1.429483280634478, -14, -1.4415805150257806, -14, -1.4293244836477403] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0208  total reward: -494.6792575405865
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9328880565321667, -1.5622329356737863, -1.45526508926673, -1.4626486379216177, -1.5662210509495194, -1.4239959638263004, -1.4072837631816628, -14, -14, -1.4519243617465267, -1.5432743402476072, -14, -1.5060535605970904, -1.4082302729567766, -1.3819820743630866, -14, -1.4094459564659172, -14, -1.394223235949119] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0209  total reward: -497.4326088666596
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9403479987745513, -1.6018603511783984, -1.454279089176891, -1.419057922500519, -1.6402018544869315, -1.3979127494068113, -1.3950688938724676, -1.5063683719515357, -14, -1.400701640058906, -1.4425151649453527, -14, -1.5147073702613225, -1.3817293201058451, -1.3646820694161985, -14, -1.3750814057024527, -1.4076048982218772, -1.3713692517100757] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0210  total reward: -500.4205188647618
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2738415900442357, -1.8491798857039399, -1.709118523532049, -1.6957912728820035, -1.9376230695126109, -1.6710854809942222, -1.6398052694186522, -14, -14, -1.6759166131235252, -1.7551950081165557, -14, -1.785206512150228, -1.6468793703274087, -1.6344874614848057, -14, -1.6357611011717887, -14, -1.6232279286859372] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0211  total reward: -503.6608166741273
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.322643177657878, -1.8328311951661538, -1.6974768266497473, -1.7176575750458478, -1.9118485325563874, -1.6849196252082281, -1.6290207207316643, -14, -14, -1.6721844747286871, -1.7598736687963707, -14, -1.7957528618131566, -1.6406258407443908, -1.6267739633176361, -14, -1.631755869167605, -14, -1.6170698806796215] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0212  total reward: -506.83357839921644
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.240992043120513, -1.762369130120406, -1.64748071737578, -1.6558718507583357, -1.9382166997769288, -1.6220292260575215, -1.5612210582144965, -14, -14, -1.6009174899687013, -1.665766296908881, -14, -1.6980645692321568, -1.5795216328511472, -1.5733020926846233, -14, -1.5654203085234546, -14, -1.5556918444094263] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0213  total reward: -509.74222244731106
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.958437760422676, -1.5102969912679498, -1.4239232718772137, -1.4586643483312085, -1.59925068848172, -1.3992608706151213, -1.3574365719319341, -14, -14, -1.3954837884887654, -1.463867081559702, -14, -1.4559281413055163, -1.3717132668894165, -1.3562829825078306, -14, -1.3645258687878448, -14, -1.3529522036851909] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0214  total reward: -512.3953312765166
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8096951355829158, -1.4650391771494296, -1.3622996426697807, -1.3613974602914038, -1.4882991431091066, -1.336296134197134, -1.3079576721269863, -14, -14, -1.3458318075749391, -1.4088814675491292, -14, -1.4020677683779847, -1.3149534388075967, -1.2969456552037109, -14, -1.309214507739366, -14, -1.3001566255202934] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0215  total reward: -515.4313817337915
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.714821777823917, -1.9303042938092856, -1.8391661352286852, -1.983439536923449, -2.066145222187336, -1.788977568767352, -1.7540972272532287, -1.8513799317154582, -14, -1.7666465666256106, -1.8059917618568855, -14, -1.8776688429375288, -1.7509289587898356, -1.728125451038347, -14, -1.7419908051858188, -1.778807858715482, -1.7391048020712387] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0216  total reward: -518.223575261095
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7872104180373707, -1.9363053324334878, -1.4856628391956535, -1.2032695740300812, -1.1169308138812573, -1.114113145354461, -1.2373742425407808, -1.0967272104571675, -1.0698562114773433, -14, -14, -1.1073636514805485, -1.1700653725846804, -14, -1.1502478248014425, -1.0779819033869493, -1.0621454581634768, -14, -1.0735788050393178, -14, -1.0640680762652055] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0217  total reward: -520.1444451245204
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4919054055226566, -1.5291040434977843, -1.1824355367533126, -0.9901108464966586, -0.9103137330710432, -0.8840644416820872, -1.0142343375213978, -0.8527086709444632, -0.8844576429991501, -0.9867780461197729, -14, -0.8782149901058528, -0.9081161664888302, -14, -0.9374364698257931, -0.8644008099286455, -0.8630687392739183, -14, -0.8622718897356629, -0.8872917814489917, -0.8587244052618833] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0218  total reward: -521.598040357904
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9784317267972771, -1.0585420897834807, -0.8250306084280088, -0.699154900498778, -0.6327855703965105, -0.6155514716795084, -0.7011317570297152, -0.5977077536072241, -0.6063942551450386, -0.6801044864914018, -14, -0.6135614173154114, -0.6235706230797633, -14, -14, -0.5993329705350785, -0.6290805425567483, -14, -0.6019937613838777, -0.6059522788298152, -0.6008865624391269] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0219  total reward: -522.8379488111284
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0811283702292092, -1.129384720417686, -0.9179145180816399, -0.7436008709738586, -0.6791306381784672, -0.670171474477619, -0.7522818679764992, -0.6392831369749433, -0.6606216862893769, -0.7305469382630274, -14, -0.6581327928585853, -0.678312896595268, -14, -0.7031268747646686, -0.6465466726472971, -0.6445564195751703, -14, -0.6439060674468066, -0.6621611459976557, -0.6422006996171534] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0220  total reward: -524.4368239405857
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.11408828318252, -1.5416818058419066, -1.1790346940694916, -0.9757587949777289, -1.0113818872474019, -1.0328327442170295, -1.1973281052837703, -0.930118751748167, -0.9623765893158118, -0.9843984099435813, -14, -0.971912064406219, -0.985331830508639, -14, -14, -0.9629998566114, -0.9672503537287334, -14, -0.960389520246718, -0.9643858251418184, -0.9595919924824101] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0221  total reward: -526.0791514225932
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1880546450979028, -1.2473033499802066, -1.0124751401213936, -0.8371811992189109, -0.7543785054697427, -0.7355866555207341, -0.8438162437082356, -0.7110307426353023, -0.7317240208010422, -0.8054902620752664, -14, -0.7298947407604682, -0.7533268639716838, -14, -0.7818747390688067, -0.7169750894373769, -0.7120887603912315, -14, -0.7142772780565432, -0.7347746478225529, -0.7122087302592953] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0222  total reward: -527.6986191593178
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5741800341140095, -1.6161981392630345, -1.2558604733606982, -1.053805621357527, -0.9640393835423694, -0.9341373316035351, -1.0942526635772578, -0.9109789922508549, -0.9210760164769092, -0.9946447247037958, -14, -0.9275371134759129, -0.9471449273884612, -14, -14, -0.9088864984155527, -0.9296034216344506, -14, -0.9113512816934388, -0.9264913742102648, -0.9084369940893341] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0223  total reward: -529.8866760920828
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.801915587773148, -1.4655082864065405, -1.3540594229264558, -1.335487096797185, -1.5197555844140693, -1.2811927879895713, -1.2964214380045207, -1.432436228459485, -14, -1.3074804125968795, -1.3297842174967365, -14, -14, -1.2787335801692852, -1.317778436298169, -14, -1.282076905387544, -1.2946054385629795, -1.2796199386757374] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0224  total reward: -532.652610129153
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0699120317008695, -1.7471573774277291, -1.568729107273357, -1.5231307120405904, -1.7247905522181948, -1.513387268369856, -1.5365125469159606, -1.6566487109526122, -1.535088332090002, -1.522325818395596, -1.5454519056425968, -14, -14, -1.4888866496916158, -1.5218267577430087, -1.5096292589923679, -1.4914339155091634, -1.5070568660795851, -1.4872004569008992] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0225  total reward: -535.2572847902752
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1137854102342584, -1.1075190842101406, -1.376264616841746, -1.26045405166342, -1.1234200140265966, -1.1205275952529516, -1.1384660969021307, -0.8928362994784776, -1.2063144517686528, -1.191412682238164, -1.1589850225057607, -1.1472281560456334, -1.166913949403695, -14, -14, -1.114287020876483, -1.1671262315142166, -1.127938501985047, -1.1198603788969084, -1.1328333788368754, -1.1174742042213195] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0226  total reward: -538.6724986894675
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.8274775213948304, -2.673905332333615, -14, -14, -2.574929521778031, -2.540815851993151, -2.6120062557684434, -2.635546939759094, -2.562909614860517, -2.6179097420074635, -14, -2.677749572858283, -2.5073036660134544, -2.5258382917298854, -2.5799818300382205, -2.5304918429119385, -2.58778691587174, -2.522377599713764] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0227  total reward: -542.7462093577162
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2060800321477347, -1.8297174143938333, -1.6546520782115686, -1.6175295354569332, -1.8381728377445337, -1.5720403254318065, -1.6105443655707965, -1.7453939603593447, -14, -1.6064420253228997, -1.657347195851335, -14, -1.7476600113544827, -1.5767659640011138, -1.5679893554986133, -14, -1.570461110576706, -1.6300818197988913, -1.5664070022352707] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0228  total reward: -546.2260549779238
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7395201304429535, -2.2339636663847826, -2.034917054186644, -1.9886348323395378, -2.297761569118849, -1.9048755923497798, -1.9599078463693111, -2.1066268851673575, -14, -1.9526902257867835, -2.014848211167433, -14, -2.059327795065478, -1.9231640071868557, -1.9028911900282381, -14, -1.920306777653562, -1.988108837895722, -1.9134386179722545] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0229  total reward: -549.8696046816265
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4840581738918477, -1.9322492826232465, -1.8277912211587102, -1.8710511532312546, -2.0369431704093373, -1.8031000612637833, -1.7513248666560783, -14, -14, -1.8000825558398181, -1.8926921376681096, -14, -1.9034944390107278, -1.7643027320337337, -1.7458203988576646, -14, -1.7558459475395185, -14, -1.7406585136744752] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0230  total reward: -553.1794527107584
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.191584316091185, -1.767794266325528, -1.6347608122026975, -1.6464622604943602, -1.753185634647442, -1.6377351562044813, -1.5713699003065111, -14, -14, -1.629941989795086, -1.7246645278377224, -14, -1.6931283571436937, -1.582913736790751, -1.5473193010325546, -14, -1.5847306406505894, -14, -1.569189515457447] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0231  total reward: -556.5736085234631
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4727739958587063, -2.100431699116666, -1.9005859843788946, -1.8877775382577444, -1.9346268724888962, -1.8513839530649776, -1.8960384668689023, -2.778327024675048, -14, -1.8621634669234193, -1.8704839540747489, -14, -2.0656820988630065, -1.8459142395154735, -1.9671998863479536, -14, -1.8461893948608554, -1.8438393452589057, -1.8468365116721457] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0232  total reward: -559.7948086655663
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8852012367991198, -1.6078777946043727, -1.4683200451294491, -1.4088138478315029, -1.8056343700747475, -1.3481698289335062, -1.4713529808004502, -14, -14, -1.3957314432186692, -1.4088683631241403, -14, -1.540277112957272, -1.3803110448816147, -14, -14, -1.3778230101300695, -1.3363141125261913, -1.377360796844373] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0233  total reward: -563.2336285188087
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2909094815826334, -2.53126060081894, -2.2663457724141822, -2.2369620267778303, -14, -2.080285172524863, -2.1664941120861725, -2.180856835603129, -14, -2.153412413096157, -2.2403219487140347, -14, -2.0802851725248623, -2.089320166766703, -2.0840376570080363, -14, -2.1133479262562456, -2.2634084973737707, -2.102505740716211] argmax 14
Action chosen: switching off line 14
  Simulating cascading failure
  ok
timestep 0234  total reward: -567.0435148613228
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.292012440036869, -1.9305020419240384, -1.789756837819187, -1.7824819907690528, -1.8552126614024087, -14, -2.417626037816604, -2.102234619201695, -14, -1.7880822641911127, -1.8228059790896582, -14, -1.566689293916445, -1.7379230475209542, -1.7287618783488277, -14, -1.7419052814313982, -1.7941897400283071, -1.7296011699892053] argmax 14
Action chosen: switching off line 14
  Simulating cascading failure
  ok
timestep 0235  total reward: -570.2907808860754
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.384105840240498, -1.9140299243971843, -1.7836883819021194, -1.767224430531616, -2.010772818079753, -1.6953672135325024, -1.7132450298028856, -1.8341186709687503, -14, -1.7189380189585008, -1.7751752097155706, -14, -1.8342738691508778, -1.6913546185427673, -1.6763281659021012, -14, -1.6862926858184262, -1.7370275726290734, -1.680576730836084] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0236  total reward: -573.6254471785462
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2949818968262448, -1.886540298884145, -1.7356967469447915, -1.7220178719042147, -1.8970177633835072, -1.6755876218060133, -1.6910139993385302, -14, -14, -1.7160259864951215, -1.8093333979946709, -14, -1.810481267094279, -1.6778044509185723, -1.6601012944335194, -14, -1.6742240768788434, -14, -1.6583381265688022] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0237  total reward: -576.4995242364773
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.5908399372455726, -1.373172978550057, -1.2617702415832297, -1.2379601772947653, -1.3270918395645936, -1.2351462885047129, -1.2321361533035875, -14, -14, -1.2653299695075653, -1.3423307568535807, -14, -1.3178884624728004, -1.2233073261876237, -1.1984252622442286, -14, -1.2283188371957956, -14, -1.2157389313623044] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0238  total reward: -579.0749804097534
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9335255853455904, -1.5395417748672096, -1.4610019144882491, -1.458113743556623, -1.632204361399129, -1.3906771137787155, -1.398733289098104, -1.52086709420977, -14, -1.4091910580123068, -1.4443273626015134, -14, -1.4872914290793715, -1.3876480736503884, -1.375235437636235, -14, -1.3787677396488371, -1.4009698948646017, -1.3770309110317702] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0239  total reward: -581.716968131836
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7974379790467903, -1.4148547580597968, -1.3309535655768985, -1.3488911058382151, -1.4745175799106243, -1.31481288756841, -1.270857426316068, -14, -14, -1.3087181737510538, -1.3668460451154218, -14, -1.370480149626282, -1.283361378279191, -1.268886492329297, -14, -1.2751362802701214, -14, -1.266752284446326] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0240  total reward: -584.0128759197905
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.693011703636936, -1.9088784770011002, -1.4309962873232134, -1.1518677103243644, -1.0732943934561328, -1.0815682926445485, -1.1478296132698182, -1.0584966689440984, -1.0357999625122312, -14, -14, -1.065019708694038, -1.1197472451022141, -14, -1.1133122432518807, -1.0385290762782988, -1.0214072509594823, -14, -1.0379366588769376, -14, -1.0291555035083637] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0241  total reward: -586.2011226828711
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4244882414203397, -1.1824806711775346, -1.2287009689464459, -1.2562189592672723, -1.441601511016122, -1.2097395388177026, -1.1740525682541343, -1.19712848939647, -14, -1.186784412284059, -1.221443610559681, -14, -1.255197268769635, -1.1737691400235881, -1.1551382127009622, -14, -1.170697413810248, -1.205634988726862, -1.1668395121210504] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0242  total reward: -588.061920021348
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1229892454737247, -1.298778990933187, -0.9595278865615924, -0.7896879168938367, -0.7325078420321285, -0.7340316232755086, -0.7731807593397415, -0.730108661863524, -0.7100559422443679, -14, -14, -0.7351188986320032, -0.7791714719433338, -14, -0.7704812158830928, -0.7104595149056416, -0.6954797613228165, -14, -0.7125775375292525, -14, -0.7056591257759116] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0243  total reward: -589.7048515718222
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.1053372934938923, -1.5001771060906486, -1.1686624164694086, -0.9614469420068891, -0.9976295698541024, -1.0263794405154263, -1.1791605979708792, -0.9848324311232427, -0.9527887252183574, -0.9656430028411785, -14, -0.9650104981461833, -0.9918597113919772, -14, -1.0184806397775132, -0.9508127593103811, -0.9367784138599651, -14, -0.9497095215927462, -0.9838129940391437, -0.9474517891515102] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0244  total reward: -591.264006683511
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0100600078202402, -1.1462342364180325, -0.8647133991370074, -0.717298822702187, -0.6514159893038006, -0.642905317896417, -0.717048899190435, -0.6485189165499927, -0.6242041479012392, -14, -14, -0.6438110374430867, -0.6758473139303535, -14, -0.6763720528389664, -0.6300873308645012, -0.6207958395724213, -14, -0.6274053636904664, -14, -0.6223766978286746] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0245  total reward: -592.8606384195023
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4766372428539944, -1.906889179593029, -1.2530684406645325, -1.1246954142009806, -1.0021148177420884, -0.9804930706807293, -1.021219472315199, -0.9702048681838502, -1.0114545705307725, -1.517755341173436, -14, -0.9859963388764735, -0.9925161538456023, -14, -1.10040566772053, -0.9774250008562188, -1.0453810165592716, -14, -0.975677733714995, -0.9741390590505673, -0.9758358964189028] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0246  total reward: -594.933699910443
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9643346117550529, -1.8654784555519874, -1.561211427330762, -1.2278706849014476, -1.1685767702925889, -1.1785557921935328, -1.327983858237904, -1.0840088384080202, -1.1000327112247434, -1.189157867596477, -14, -1.1223165092945733, -1.1378228761121767, -14, -14, -1.1044872095665688, -1.132821977140015, -14, -1.1036994793888268, -1.1110433393664678, -1.1028566227569552] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0247  total reward: -597.3737388808684
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9067261744445083, -1.5786264129221301, -1.4376683434715134, -1.4010808427862032, -1.607310430884691, -1.363580930153952, -1.3853073417590867, -1.52155283751727, -14, -1.38353256088683, -1.4235583493558492, -14, -1.4826283388182282, -1.3657490505168588, -1.356031330639361, -14, -1.3598677649870334, -1.3964482141600782, -1.35603013201726] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0248  total reward: -600.1346065982207
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9876553528688126, -1.6584679399435511, -1.485391614805356, -1.4449926417399772, -1.650000572078214, -1.3910308016104596, -1.454855609435345, -1.6016956544396812, -14, -1.435631621530632, -1.4770266786717139, -14, -1.5507730873851662, -1.413088747941133, -1.399247045903718, -14, -1.4082202943105437, -1.4615048284141106, -1.40483758533496] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0249  total reward: -603.0657725215701
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.144776909788841, -1.79096024353261, -1.6309482316726809, -1.5867488163556516, -1.8429035630110016, -1.524038804037147, -1.5414684271285193, -1.6933977395334492, -14, -1.5750785136960737, -1.6038747630536823, -14, -14, -1.541050125695528, -1.5978474000549405, -14, -1.5428245664341682, -1.5516620551132863, -1.54013512173905] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0250  total reward: -606.3828857207819
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0160930767536516, -1.844350169080571, -1.8947596504474025, -1.8138872717365189, -14, -1.8298977160867882, -1.8229820665197087, -1.8904047938650987, -14, -1.8374728562193374, -1.9060099916364166, -14, -1.980034531695912, -1.8046567933604534, -1.781210336948574, -14, -1.8009537459982201, -1.8533973752811626, -1.7930743951746808] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0251  total reward: -609.8990881813602
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.399003076993817, -1.966964331821731, -1.8114694846842399, -1.8051841439472114, -1.9654642364268646, -1.802828991067725, -1.7430525819890113, -14, -14, -1.7972139316347, -1.895683736112775, -14, -1.8940061107086865, -1.7544562225216411, -1.725030007454099, -14, -1.7513950526194864, -14, -1.7349921236296502] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0252  total reward: -613.2857757148164
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3048745349277384, -1.9295653968176427, -1.7538468260211701, -1.7096238469702685, -1.930498078675427, -1.6811278920919355, -1.6959059034208745, -1.9099698639126916, -14, -1.6994785441157618, -1.7457028494565079, -14, -1.839084038067206, -1.675496091485998, -1.6817459989689723, -14, -1.6651669233895654, -1.696322446139588, -1.6616575260021411] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0253  total reward: -617.0728058343985
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.5541315077299953, -2.1546297488096537, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0254  total reward: -620.9552175846688
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.4916043253123537, -1.821006328298363, -1.754177549371554, -14, -1.753568915955559, -1.7469546256837227, -1.9950094392420097, -14, -1.7666333649436103, -1.8233042602157261, -14, -1.826731190067569, -1.7461475182959698, -1.7022579777474602, -14, -1.7311481219453562, -1.7872285103430174, -1.7277820014605936] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0255  total reward: -623.8343347380337
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.002136380922371, -1.6220779596799433, -1.472917241474159, -1.4463061641099895, -1.6580497795420444, -1.3901432525099615, -1.418959091916156, -1.5267702842105335, -14, -1.4187810582480536, -1.4615802930882482, -14, -1.50923269380545, -1.3954419137152914, -1.3789081522818596, -14, -1.3911816298917596, -1.4304571343503028, -1.3875128280525655] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0256  total reward: -626.3743766998839
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9128952887240271, -2.1430779898042944, -1.5639278220048836, -1.3237271234059484, -1.215274085789906, -1.191279137794885, -1.3316695651947559, -1.1826154084270966, -1.1786788870155323, -14, -14, -1.2078859526308388, -1.2778814907845009, -14, -1.2720474366643295, -1.1752089698142811, -1.1602890946842908, -14, -1.1721407881616732, -14, -1.1611338095683337] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0257  total reward: -628.9366467517
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.974557515741999, -1.5859701915128273, -1.4864809324175159, -1.4761838962561187, -1.6725008939491552, -1.429398791152771, -1.424206500388311, -1.502780511335489, -14, -1.436890834100023, -1.479276403104112, -14, -1.5404056734258098, -1.4109376985928, -1.3985084717838354, -14, -1.40473655973355, -1.4515215585573968, -1.4019809571318398] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0258  total reward: -631.1747017397508
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8884147627118704, -0.8718179911794969, -1.043370236556323, -0.9832617660068964, -0.8190979681027013, -0.8389251862261085, -0.837796025984919, -1.0742029753027709, -0.8356829660622425, -14, -14, -0.9006321466605969, -0.9965213486298327, -14, -1.1228396338195343, -0.8441954491761233, -0.8286979831713661, -14, -0.8553883481491681, -14, -0.8395465162670278] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0259  total reward: -633.4597684907326
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.900740905229311, -1.6525426460717243, -1.411448345988551, -1.4937867322258462, -1.6358295911719694, -1.50542285495385, -1.4845313401900841, -14, -14, -1.5219477875983924, -1.6145062315113192, -14, -1.6190751067874478, -1.493585615642966, -1.474545030458049, -14, -1.4820710800556425, -14, -1.465968782879045] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0260  total reward: -636.3212247325282
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0058936902999007, -1.6151343801481146, -1.5178121812211969, -1.5262329304849531, -1.6511086342478138, -1.4833169858303914, -1.4649788092637726, -14, -14, -1.498951907126397, -1.5838349036816675, -14, -1.5765324369504756, -1.4667940240849495, -1.4460025034480946, -14, -1.4654603158026598, -14, -1.4500078958070541] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0261  total reward: -638.9772930568183
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6584600319473544, -1.4050059959033157, -1.2770631337381657, -1.2388134652599383, -1.3982105547981434, -1.210245948178744, -1.242000941929054, -1.4177006788508175, -14, -1.2360990233231843, -1.270506517623886, -14, -1.3323626719375912, -1.2191754947756022, -1.2272190142308486, -14, -1.213260315481639, -1.2385663533300932, -1.210065820842091] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0262  total reward: -641.8971947876124
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0488860308270977, -1.7327347786686902, -1.8015644314090624, -1.815722037773196, -14, -1.7799628465681805, -1.7194104809506408, -1.7762703810540912, -14, -1.7402894412766332, -1.784921647842346, -14, -1.8459768813738897, -1.7207411205408938, -1.698512089789851, -14, -1.713406987468924, -1.7590909499907141, -1.7098359099519271] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0263  total reward: -645.3758199774883
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.250639092321965, -2.0075730309301996, -1.7713423966524682, -1.7906495820717645, -1.7260911812586985, -1.8404212086294505, -1.7893578946486906, -14, -14, -1.825829851974651, -1.8979958000410078, -14, -1.9321855314175704, -1.7363935156353878, -1.6765750644642619, -14, -1.792103498298393, -14, -1.7801131000860497] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0264  total reward: -648.0446313082662
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6286838454887644, -1.7435450865020732, -1.3939738074952899, -1.163710161445621, -1.0477676376167233, -1.0211572869379848, -1.1595744361278362, -1.012979545766934, -1.0084022562673913, -1.124165967969412, -14, -1.0140716096432951, -1.042581604738807, -14, -1.0986314638295536, -1.0010033320518668, -1.0001831964394017, -14, -0.9946854976686568, -1.0084871565803544, -0.9922362663135883] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0265  total reward: -649.7919032367067
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2651851061079076, -1.3331080736522058, -1.0532965225235398, -0.8942986877876086, -0.8007215032523888, -0.7716723254227948, -0.8993802846059226, -0.7517189204885378, -0.777501028303165, -0.8352819305661509, -14, -0.7748648589001845, -0.7991301151628527, -14, -0.8293001187963164, -0.7595034379719781, -0.7500016252877701, -14, -0.7567262250290034, -0.7834414328860663, -0.7550356621270322] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0266  total reward: -651.5057512823339
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3627268541612898, -1.9718234113494968, -1.1969230502399577, -1.077672811304654, -0.9653866272996491, -0.9670518879307924, -0.9374232964160608, -0.9849558843417707, -0.9707658395103791, -14, -14, -0.9874542570856388, -1.0232367044962811, -14, -1.0336645857203908, -0.9411882147587357, -0.9114914444052928, -14, -0.9695472309073618, -14, -0.96384642033941] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0267  total reward: -653.16030536704
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3367773048295755, -1.2937342396170257, -1.0550211778216687, -0.8290963276093806, -0.7875764480791494, -0.792793591008655, -0.8770360963676819, -0.7455403387354993, -0.7578012507170021, -0.8366635830189991, -14, -0.7594208054350139, -0.7794612411748104, -14, -0.8036126770020552, -0.7483042136122569, -0.74654834681308, -14, -0.7444694618987284, -0.7623738981768164, -0.7430626403007565] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0268  total reward: -654.5095118859774
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0217606550747707, -1.062519804465349, -0.8562967595206697, -0.6996916539271584, -0.6408334712032422, -0.6304829846614701, -0.7095864655343656, -0.5997432025581729, -0.627697749940029, -0.6943025666277375, -14, -0.6209611282478297, -0.6427181998801414, -14, -0.6675278312974744, -0.6096129855998912, -0.6081385261807394, -14, -0.6086259790600932, -0.6289912471459761, -0.606143878636624] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0269  total reward: -655.8279411555527
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2520688646028066, -1.2098368094040524, -1.0403597787650842, -0.8356311337230503, -0.7661487856774366, -0.7536332943586054, -0.8997029530063406, -0.7087119680807117, -0.7158945489171955, -0.7550031917447594, -14, -0.7312717661341475, -0.7465808081759592, -14, -14, -0.7202822713134299, -0.7260623416288008, -14, -0.7205442261493993, -0.7301255783882163, -0.7186860670171209] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0270  total reward: -657.6020563382224
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.2667874470233824, -1.077104202874245, -1.121302465313257, -1.1288854431817996, -1.294392089892804, -1.0986891802921037, -1.0752378033443866, -1.1082370425027386, -14, -1.088198934925896, -1.1231732247377395, -14, -1.158458264486166, -1.0721671351762485, -1.0593404967813875, -14, -1.069135889332367, -1.0960413266266618, -1.065403214588983] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0271  total reward: -660.2531034910141
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9882565527415021, -1.7408360894191959, -1.5908317833958798, -1.6116646586569314, -1.5294409351715785, -1.6574387421938888, -1.5918745405922279, -14, -14, -1.6366872536187218, -1.7003149027448772, -14, -1.6935420300211699, -1.5341636538954806, -1.4763065283719923, -14, -1.6011074373270644, -14, -1.5917066560103672] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0272  total reward: -663.2919606873878
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3073416595772, -1.7778347413786146, -1.6586238108855167, -1.6796417153771586, -1.8764647862598578, -1.579208033005665, -1.5884924680836037, -1.6896468067807757, -14, -1.5949086551671237, -1.64055711622701, -14, -1.6915276681607168, -1.5725474153033856, -1.5541345483120586, -14, -1.5663917390599729, -1.6170955638474673, -1.5625506680016172] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0273  total reward: -666.3712813662839
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.135303264086907, -1.7095980078363266, -1.6008135061053403, -1.60932978643333, -1.7747859496056693, -1.5792941298391328, -1.5333004056994288, -14, -14, -1.5798145036411935, -1.6683821765453932, -14, -1.6607235481847495, -1.545505542962482, -1.5252415652981062, -14, -1.5403003895079557, -14, -1.5251861305841428] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0274  total reward: -669.5070875887371
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1076028278160135, -1.8272916537732589, -1.683721220085515, -1.6380582885871824, -1.824222027029026, -1.6356647312179622, -1.6373426494207648, -14, -14, -1.6699444186827757, -1.761097426239968, -14, -1.7619212775186814, -1.62858211290287, -1.6066296533964313, -14, -1.6253513832307291, -14, -1.610620091869014] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0275  total reward: -672.4654230737993
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.810537564077522, -1.5542933965084507, -1.4210588980246013, -1.3797350562880768, -1.5464094562074464, -1.363584028806487, -1.3898385774511304, -1.579524537134987, -14, -1.3895084781455893, -1.4331725058631382, -14, -1.5329222110971543, -1.3626670920813753, -1.3785145327237813, -14, -1.3552672084958823, -1.381176629576787, -1.3517058316657498] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0276  total reward: -675.7659519319369
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.794228421754758, -2.2370857318973543, -2.071161724414594, -2.0480360335970094, -2.3349190629450676, -1.944416429966102, -1.9944286773867546, -2.180796713012303, -14, -1.9875199615681014, -2.039793366259338, -14, -2.103034304913366, -1.9602302875334219, -1.9392844759474817, -14, -1.9526830682880785, -2.0159824309120293, -1.9488230264718185] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0277  total reward: -679.1978495587244
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.122351867697284, -1.667009356871371, -1.5573410160715984, -1.5918877570295311, -1.6830502484522736, -1.551442045104597, -1.5027154355969257, -14, -14, -1.5425422921193233, -1.6184506082140668, -14, -1.6462852307790414, -1.5098748230580301, -1.490224700378819, -14, -1.504745551906213, -14, -1.4926131508400222] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0278  total reward: -682.1840542510848
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.115900290232197, -1.7138591142941526, -1.5904061153343347, -1.5652426140051952, -1.8082168675795527, -1.5072791202935367, -1.5258727428731216, -1.612573866621256, -14, -1.5297972902763197, -1.5755121466440594, -14, -1.629011847513012, -1.5046448909894106, -1.486059069183283, -14, -1.4994161627737612, -1.565123207575051, -1.4959799919816374] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0279  total reward: -685.020448606328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.806728617857523, -1.5498389780737176, -1.4135717033671513, -1.377735511501731, -1.5530237995434928, -1.3883114041318494, -1.362701364545096, -14, -14, -1.398051677066517, -1.478084223553757, -14, -1.475596356680028, -1.3675488532259943, -1.3463527950131031, -14, -1.3644517920491468, -14, -1.3503352860599274] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0280  total reward: -687.650373304856
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.792940066423803, -1.4741583752044847, -1.3574440335285265, -1.3317137499219436, -1.4965536117503446, -1.2856711683523918, -1.3144509196537209, -1.4942611949488875, -14, -1.3092381013041543, -1.3391411189208848, -14, -1.405222236571173, -1.2934023265266967, -1.289763251275656, -14, -1.2852346237252297, -1.311057118765102, -1.28357190351487] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0281  total reward: -690.2060593320065
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8043526584288494, -1.4625591086316259, -1.3422283595653932, -1.3281050423619734, -1.4712822856909888, -1.2731519080503784, -1.3038503763170821, -1.472433225015242, -14, -1.3051848893475135, -1.3458931090958035, -14, -1.396559682515799, -1.2820531424438195, -1.2872570009672792, -14, -1.2758959007833488, -1.2929608920906601, -1.2721141236355664] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0282  total reward: -693.0304984145282
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.185521495002997, -1.7876740446980255, -1.6487739672289392, -1.6151697212149556, -1.8624509150483517, -1.5598495021971537, -1.5854529674507065, -1.7174167834903444, -14, -1.5889099447757444, -1.6408581389570378, -14, -1.6918961140016968, -1.5632756777302026, -1.548583744336213, -14, -1.557343018641722, -1.6013431485804683, -1.552324958886129] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0283  total reward: -696.5856863785557
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.328356245199427, -2.0047449413512264, -14, -14, -14, -2.1387038927501356, -2.0049806394406917, -14, -14, -2.064306696245666, -2.1474223723948422, -14, -2.1836305833715874, -2.033916112877446, -2.0066868293840048, -14, -2.019136171638779, -14, -2.0066042196913205] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0284  total reward: -700.2411357574899
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.4827501310147897, -1.7381593270385125, -1.6515843122865752, -14, -1.7029648299269269, -1.6601222210784412, -14, -14, -1.6989861314932089, -1.7671200936099856, -14, -1.789354598536664, -1.6899913464717513, -1.6810423165267299, -14, -1.6607437505699443, -14, -1.650704437582911] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0285  total reward: -703.0751089241205
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9195463548407135, -1.5187043138780407, -1.4259386634969804, -1.4347873132576798, -1.6308907915153554, -1.3931418787464578, -1.361442886009789, -14, -14, -1.391766060199883, -1.4590472311033318, -14, -1.4747208737665278, -1.3706442992903471, -1.3616361221330364, -14, -1.3629693910279492, -14, -1.351223035615807] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0286  total reward: -705.6681612142152
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7441241895736719, -1.377251869115628, -1.3022095922906547, -1.3230926024911938, -1.434890499260906, -1.2898990234310987, -1.2476800850998544, -14, -14, -1.2837573196811993, -1.3460426660438236, -14, -1.3552473177284123, -1.2577132120577894, -1.2421156040094061, -14, -1.2515422768355302, -14, -1.2418292544788447] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0287  total reward: -708.0629642185514
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.84350629406774, -2.129454298472301, -1.5754336108557239, -1.3308505177163827, -1.2037292684933754, -1.182317355773442, -1.31374917886699, -1.1885095272678765, -1.1630102152382966, -14, -14, -1.195854138585106, -1.2593346365630973, -14, -1.2636763665017838, -1.1667496280125738, -1.1492281637529584, -14, -1.1628363940094721, -14, -1.1529737498574728] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0288  total reward: -709.9099649694854
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1645379773613094, -1.1923973258118752, -1.0165605104493962, -0.8004697720171206, -0.737292614063769, -0.7398516274101106, -0.8183507358553278, -0.7031016639011293, -0.7129881681018457, -0.7748285684387388, -14, -0.7148443825800229, -0.7402546639719125, -14, -0.768249818530301, -0.7028215736310616, -0.7020075658133714, -14, -0.7007799584838185, -0.7180571894149206, -0.6977725871810768] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0289  total reward: -711.1737584050463
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9857136864761593, -0.9931357544785094, -0.7889134418473482, -0.6476712408809673, -0.5999843283484046, -0.5882824840500376, -0.6698345752595146, -0.5696866698907261, -0.5773050070032101, -0.6382239232369264, -14, -0.5799004780083518, -0.5975310446221384, -14, -0.6167701696756748, -0.5705312743259668, -0.571902237466522, -14, -0.567480281099071, -0.5828620453950792, -0.5660208483798794] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0290  total reward: -712.2261026944116
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8483168220071609, -0.8669814397328547, -0.6620986448550716, -0.5603622726363389, -0.5156664434136474, -0.4986870596262194, -0.57502977257765, -0.49043405007663865, -0.49619271341424065, -0.5559574074172972, -14, -0.49747932912392423, -0.5094056656148288, -14, -0.5329380772430856, -0.4902764279309538, -0.4869040382377898, -14, -0.4868103377589182, -0.4955189691177385, -0.48632344098530095] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0291  total reward: -713.201525127002
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0645073941911711, -0.8005890323806257, -0.5664353522715233, -0.49844899387681857, -0.5155441491274714, -0.5055994207156835, -0.5938962500432919, -0.5056870986284202, -0.4943630607503981, -0.5119750882892922, -14, -0.49956632697923714, -0.5152983460791124, -14, -0.5376996492952223, -0.4924116873572346, -0.4869706293517201, -14, -0.4906514727879855, -0.5066101296632854, -0.4890989916052936] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0292  total reward: -714.2205987282739
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.135596432831899, -0.876206366835129, -0.6454196444687565, -0.5350880588605039, -0.5582945200633346, -0.5749772313007531, -0.6485712293355479, -0.5643563864266183, -0.5324284707423166, -14, -14, -0.5464221541548114, -0.570319680575114, -14, -0.5845400148771415, -0.5399867941094804, -0.5366011252248906, -14, -0.5362979958110918, -14, -0.5321029719200594] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0293  total reward: -715.2785141157563
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8567063232495071, -0.9176912607203003, -0.7621399674528968, -0.5807688457126657, -0.5491138546051738, -0.5727901442353293, -0.596379580706325, -0.5570554904099723, -0.5260020869285598, -14, -14, -0.5420357449483675, -0.5663822268397667, -14, -0.5753715458116998, -0.5318769072663196, -0.5239831922050409, -14, -0.5296506280099149, -14, -0.5258124155623997] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0294  total reward: -716.1098981522534
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.31272449927566726, -0.3104587157038637, -0.38413720594570855, -0.3526151596591966, -0.30570654811100395, -0.3081945199858139, -0.30906650305948624, -0.39969944853901407, -0.3066332316935172, -0.3179490396687682, -14, -0.32204852180811416, -0.3377039977393765, -14, -0.4187659516430296, -0.30899830229497444, -0.3116388662003834, -14, -0.3090025331609374, -0.32228358350806335, -0.3074008442919721] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0295  total reward: -717.165816688271
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1204630627697276, -1.1074929871015615, -1.0006900969555168, -0.8671293688954136, -0.7115806879013862, -0.7606133562248716, -0.8448565866174761, -0.7513725769640148, -0.768314425753882, -0.891453099708286, -14, -0.7681096563824693, -0.7930825127839413, -14, -0.8172484332023027, -0.7576972435473704, -0.7459484439175218, -14, -0.752221126232914, -0.7716494581853532, -0.7502119879066991] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0296  total reward: -718.7519052009789
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4850681718048255, -1.5346740971504185, -1.2165542482352563, -1.0014429107159681, -0.9239844367292744, -0.907681452746679, -1.0197635633141304, -0.8792987549506278, -0.8954296414434082, -1.0041211154199787, -14, -0.8975144660397636, -0.9223523655561974, -14, -0.9664613249523194, -0.881409859914815, -0.8820152516856276, -14, -0.8759302643618988, -0.8935978694803809, -0.8745078248063055] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0297  total reward: -720.6669904283594
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7879781338633787, -1.8042952162266699, -1.4700469393460875, -1.1759637676957455, -1.0994452466841278, -1.0972023856969486, -1.2129966649108899, -1.0449334368239693, -1.0661624264010505, -1.175716426487152, -14, -1.0634832720938214, -1.091379915800678, -14, -1.1483948087956894, -1.0480884615567978, -1.0425591955876328, -14, -1.0424876596916748, -1.069111654978707, -1.0405774025743513] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0298  total reward: -722.9126092291997
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4024044131279858, -1.2249378190119644, -1.2681228958746467, -1.2541439966297032, -1.4733646522116992, -1.2475683295011757, -1.2188189776136569, -1.2451103434036361, -14, -1.2327675100436482, -1.2756938869150865, -14, -1.330420180199712, -1.2114122015794002, -1.1964053764249754, -14, -1.209561112577525, -1.2567900279696496, -1.2050413982658306] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0299  total reward: -725.2011561873826
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7700004652514776, -2.0285044437282207, -1.4935927725161497, -1.2255274255303403, -1.1365740312167392, -1.1368123518857602, -1.2083740792061215, -1.1193653850440515, -1.1013625083996568, -14, -14, -1.136547548117375, -1.2045177835193372, -14, -1.1834187035075392, -1.1011243030542688, -1.0793494205925067, -14, -1.1030826070951507, -14, -1.092141581758076] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0300  total reward: -727.2298291634049
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6540975706893606, -1.6694988313702894, -1.3064882731335599, -1.098222059605701, -1.0081112614425405, -0.975915797370408, -1.1349405918426099, -0.95280366250655, -0.9705737179624304, -1.0445555516016247, -14, -0.9743731913743512, -1.0072242323105494, -14, -1.0363668690123022, -0.9559541910194893, -0.9486293978783481, -14, -0.952219993283045, -0.9814777201842222, -0.9493235554297422] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0301  total reward: -729.1534220106975
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.629747722044148, -1.761283551871085, -1.347538830105176, -1.119190473210761, -1.0259205720118545, -1.0077882100341904, -1.1587365135270118, -0.9899853909147935, -0.9915915651978648, -14, -14, -1.010663607297085, -1.072029029323727, -14, -1.067784312705221, -0.9880050667815432, -0.9803740155771878, -14, -0.9860420814693996, -14, -0.9749634494142145] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0302  total reward: -731.1078909988322
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6836389910866236, -1.808569943246051, -1.3619642902209694, -1.1022887895094033, -1.0295191173050795, -1.026172143121516, -1.1394139715688474, -0.9981432049033351, -0.9890766248700786, -14, -14, -1.0119215451011772, -1.062703145767347, -14, -1.0549270467300957, -0.9919434167460969, -0.9803091817999797, -14, -0.9878777609095492, -14, -0.9795055387205253] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0303  total reward: -732.8566437520069
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.239636510365555, -1.3934280975353979, -1.100249126809095, -0.8776765214575928, -0.8042340223561218, -0.8101972888147131, -0.8806966783052037, -0.7928813025877095, -0.7754371367532116, -14, -14, -0.7961356552696615, -0.8363616339833384, -14, -0.8407659056529889, -0.7787226919339391, -0.7689030707867404, -14, -0.7755677579259544, -14, -0.7692472144541813] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0304  total reward: -734.5324682513142
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5550818525389467, -1.7018271822772364, -1.2886283863674768, -1.125928392837591, -0.9687550186101616, -0.9161298570984154, -1.109992580582216, -0.9050800850628938, -0.9645062581637092, -1.0346573868010835, -14, -0.9333578120911943, -0.9721979565602787, -14, -0.9050800850628947, -0.9055970527766036, -0.8995819659897267, -14, -0.9117637615529229, -0.9650194837865755, -0.9069214285205389] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0305  total reward: -736.5257084536781
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9365175854871672, -1.9151552146198676, -1.6035065789345833, -1.2029259110191224, -1.1533928081190221, -1.2046709421876995, -1.3091709710675736, -1.1175870836897057, -1.1037392884440531, -14, -14, -1.1208933980188087, -1.1583959749885382, -14, -1.1818937759353312, -1.108646460873793, -1.102578227829635, -14, -1.0990305165611298, -14, -1.0936582363742473] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0306  total reward: -738.5143736754962
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4702292456345443, -1.6320448852997818, -1.243178788568153, -1.0037860984381546, -0.9348540646990862, -0.9395547328620987, -1.0113698151185888, -0.9225303886208087, -0.9024727024432286, -14, -14, -0.9322786874966074, -0.9764123316315743, -14, -0.9794172394333188, -0.9051127336738003, -0.8923335044093689, -14, -0.9002227555611229, -14, -0.8950069854437986] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0307  total reward: -740.3852445967852
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7006544793160745, -1.6834572762795765, -1.4075767928107081, -1.1227453967943266, -1.0389219718753746, -1.030809033913461, -1.172702508322231, -0.9875775069058803, -0.99592295037611, -1.0618123999876723, -14, -1.0034982665249663, -1.0364774333666746, -14, -1.0624052315792485, -0.9852726747335895, -0.9756271097357536, -14, -0.9814341976130438, -1.006583497178017, -0.9785374168796863] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0308  total reward: -742.1282292433955
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2380810493492154, -1.3853028593660044, -1.0609143642026773, -0.8498028336892974, -0.7982428703395057, -0.8109462838402153, -0.8480285701860837, -0.8027563448626943, -0.7695284480795012, -14, -14, -0.7964891923556392, -0.8416629139847565, -14, -0.8385704950898012, -0.7726396571183429, -0.7590882303219815, -14, -0.7747277416570644, -14, -0.7673575368744882] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0309  total reward: -743.6586635904339
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3506585022280342, -1.3411055147114244, -1.0650420675833046, -0.8751710439734943, -0.8172557323042908, -0.8025758794232281, -0.9120929520732335, -0.7820620207250145, -0.7854912534043926, -0.8651127165369906, -14, -0.7883613935235778, -0.8100447903996205, -14, -0.8480965866028544, -0.7773608585540953, -0.7754637610207179, -14, -0.7729523857557585, -0.7927437302085155, -0.7713461167163925] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0310  total reward: -745.1800960080834
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.253630782873541, -1.3379029449183342, -1.0279188095942524, -0.8750268277154976, -0.792341534341008, -0.7666674110929445, -0.8742825002429123, -0.7463147210207876, -0.7737902778305026, -0.8673855258494364, -14, -0.769048072786008, -0.7931267760083185, -14, -0.8289222477372955, -0.7553685664336358, -0.7594578953513919, -14, -0.7521635290864652, -0.77882853564262, -0.7500863009331105] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0311  total reward: -746.6675707941463
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2732214656356722, -1.2991022519386004, -1.0305771978525533, -0.8610765247412957, -0.7865763559050197, -0.7635424495720377, -0.8967276107629553, -0.7407781013863778, -0.7470395172564747, -0.8041075062778825, -14, -0.7567405468480364, -0.7713693164841727, -14, -14, -0.7410049231611069, -0.7638830965346111, -14, -0.7428816514864158, -0.7620313357338623, -0.7411600650420765] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0312  total reward: -747.922883238031
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8787165901988505, -0.9119657724297233, -0.7144484807319875, -0.5997662638137853, -0.5454267607816806, -0.5286738130235189, -0.6093293530142004, -0.5152187574702334, -0.5274144917719072, -0.5822837287101738, -14, -0.5261235004445238, -0.5403686295245329, -14, -0.5642278216566899, -0.5182852207166208, -0.5131268095914047, -14, -0.5154745436811311, -0.5284579435699014, -0.5145343424983354] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0313  total reward: -748.6224015827148
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.1942298570027785, -0.1885874555227005, -0.2739884543039981, -0.31800360620381357, -0.18618498499661063, -0.1961150798522231, -0.22380189131475953, -0.18787850956835506, -0.21017908148121128, -14, -14, -0.20333989542699224, -0.22930349251776977, -14, -0.18787850956835522, -0.17475147320340134, -0.1835904244946376, -14, -0.19057445461095368, -14, -0.1863915350924356] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0314  total reward: -749.1774765832558
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.628465779813092, -0.664809465743482, -0.5045199707598351, -0.4364177231519186, -0.4003217868917377, -0.38727970945690765, -0.43345486265901745, -0.38666506302309445, -0.38731710609397924, -0.44930623502003664, -0.3932634050362499, -0.3940079571872037, -0.41274066418659117, -14, -0.42495929740082167, -0.3755377716118781, -0.3784774347413208, -0.3829094446220724, -0.3829886003927064, -14, -0.38032352733763686] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0315  total reward: -749.8991089817387
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5938745868879997, -0.6177095868488814, -0.4926829075176579, -0.37894681712708206, -0.3627632346095933, -0.3754703053998577, -0.39633747243102346, -0.3572707999714648, -0.34784534147062895, -14, -14, -0.35724597324763974, -0.37466627055979757, -14, -0.37446285941013774, -0.3501637127412318, -0.34566019583577046, -14, -0.34895843686618644, -14, -0.34609462687094245] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0316  total reward: -750.5572845876983
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5324641359042388, -0.549919481484692, -0.4315124688279795, -0.35779173948290205, -0.33025025853397033, -0.32336835946979686, -0.36450582911862134, -0.3162188489964214, -0.31881092208774076, -0.3573162890384808, -14, -0.31984041861802215, -0.3281255046317363, -14, -0.3452635960646188, -0.3151402883731932, -0.3147585714752916, -14, -0.3130130273127808, -0.31823235658255955, -0.31251541012385164] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0317  total reward: -751.473558309902
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0477374742699619, -0.922007781243786, -0.9700359448850936, -0.6607310425867826, -0.6381761086112008, -0.7171795678949948, -0.7328807339373987, -0.6281363015234531, -0.6068624725172185, -0.6182356271419277, -14, -0.613257846086292, -0.6301016971408375, -14, -0.6484316600783449, -0.6062525319639327, -0.5973398798688135, -14, -0.6055937616500969, -0.6244641133693972, -0.603758312079896] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0318  total reward: -752.5196697650787
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7027922463970533, -0.8276513478510124, -0.6106127792631086, -0.5117819380248474, -0.46604068780431807, -0.4620930917619399, -0.49703829128223515, -0.46090622118399205, -0.4543422243702078, -14, -14, -0.4655328876544094, -0.49328018340015267, -14, -0.4953216616261375, -0.4530914473129427, -0.44534294697647975, -14, -0.45360437467279385, -14, -0.44877157530782225] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0319  total reward: -753.5863421508747
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0504859078375126, -1.108355498508908, -0.8551083066015501, -0.7253984279199687, -0.6575457456449881, -0.6357984463347568, -0.730022390896847, -0.6199530260935349, -0.6388757259857101, -0.7126907175877114, -14, -0.6376033380865483, -0.6569494386966546, -14, -0.6837004867614543, -0.6258696611730319, -0.6236345498268473, -14, -0.6227580964110608, -0.6377679154647883, -0.6213294388195265] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0320  total reward: -755.1173165958294
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6073452649529476, -1.7539659136649348, -1.241843234487048, -1.104321216192937, -0.9714615769972379, -0.917083111889082, -1.1154654346834982, -0.9161809616805948, -1.1684956457262161, -1.033805744856672, -14, -0.9396674060929372, -0.969864902093417, -14, -14, -0.9090258139928764, -0.9108980103725848, -14, -0.9193262587662406, -0.9866187934938692, -0.9110214188612226] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0321  total reward: -756.6201986692738
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5925807979892546, -0.589926329042619, -0.7118667914279836, -0.6775831280460342, -0.5966952591052633, -0.5920922765954374, -0.6055414106702973, -0.4724742529938802, -0.6418636521129766, -0.6261652301853168, -0.6109399393829457, -0.6101765410245393, -0.6218548513785782, -14, -14, -0.5909889209360533, -0.6185243788279997, -0.5974010065796506, -0.5955762323114419, -0.5976848279438595, -0.5938562594514525] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0322  total reward: -758.0054117056661
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6041460732853803, -1.5735164235266723, -1.3013326823374083, -1.0454161347680555, -0.9699184572048154, -0.9579291887941603, -1.0723455458740372, -0.908742561388289, -0.9305906735720285, -0.9842221363204186, -0.9583755099338734, -0.9335888366353801, -0.956394864593102, -14, -0.981576142346645, -0.9064692211815807, -0.9168460466359145, -0.937739826764055, -0.9157371893968297, -0.9352505702449418, -0.9127387833984181] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0323  total reward: -759.8164576024666
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.587376959984773, -1.617176498210162, -1.2705251214748667, -1.0358587646379762, -0.9589811809370297, -0.9423469248824015, -1.0656265423801903, -0.9058380761611521, -0.9228882205651389, -1.0366694135801, -14, -0.9257837350611058, -0.9508546673620986, -14, -0.9758192053750175, -0.9118830106308663, -0.9116996628690988, -14, -0.9063515255612277, -0.9222207721842163, -0.9045766756189014] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0324  total reward: -761.5776534081249
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5208423870268672, -1.4835372174991532, -1.1921381904430395, -0.9690027672370068, -0.9088935281717179, -0.8963081635242254, -1.0206172544878622, -0.861973976863553, -0.8743451874844136, -0.9427385593191097, -14, -0.8760124097584212, -0.9028538695337327, -14, -0.9346359092330342, -0.8628279060364842, -0.8554674741364011, -14, -0.8590513367643632, -0.884940876141861, -0.8566191300393936] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0325  total reward: -763.2839658232309
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8191494564478345, -1.464469509487304, -0.9694154333430542, -0.8586292031535862, -0.894042070350215, -0.8765570440810935, -1.0147545548633548, -0.8880113005937899, -0.8551919258591292, -14, -14, -0.8789025594389405, -0.9214653772320964, -14, -0.9375957108486757, -0.8629355327321359, -0.8558782224520467, -14, -0.8576320103600397, -14, -0.8508449409696565] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0326  total reward: -764.9020545602739
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3330607010626956, -1.4349798849504276, -1.0751238046294171, -0.8620609622858714, -0.8067188698891529, -0.8072249730791173, -0.8896138070459949, -0.7779724893920954, -0.7748371152212427, -14, -14, -0.7893665503030647, -0.8251628705633467, -14, -0.8184245134166591, -0.7764516679733348, -0.7677247725815375, -14, -0.7733405873242194, -14, -0.7672437960733356] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0327  total reward: -766.2882452989588
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9735508594576777, -1.1475134015990605, -0.8012959466901568, -0.6827478450646567, -0.6390388923427913, -0.6352673065603537, -0.6583020513420386, -0.6494919601181813, -0.6208086591967086, -14, -14, -0.6450118967606399, -0.6874482915366747, -14, -0.6803218168695633, -0.6203466286502741, -0.6025518875168039, -14, -0.6262188807796516, -14, -0.6189469426116275] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0328  total reward: -767.4669175892066
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0068007231484226, -0.9924033094981677, -0.8168268512136218, -0.6494490740749044, -0.6099612795805851, -0.6098167020515499, -0.679243887577501, -0.579490744818674, -0.5886832798552599, -0.6442585910228233, -14, -0.5886648900598552, -0.6044728034618332, -14, -0.6311871344569839, -0.5804451793132916, -0.5751852805570538, -14, -0.5772571529111693, -0.5907845965927813, -0.5761204027309282] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0329  total reward: -768.6691686925014
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0112987615140874, -1.1721293985226788, -0.8515275689286458, -0.6999893351160807, -0.6510721690400761, -0.6524499246599595, -0.6842164587111784, -0.641166287905766, -0.6342826773143145, -14, -14, -0.6536101003951125, -0.6917795102383423, -14, -0.6840337425550485, -0.6319245962680402, -0.6201290694504646, -14, -0.6328099576197918, -14, -0.6270658227378161] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0330  total reward: -770.1659451902678
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.501778008716786, -1.4954613304285378, -1.2705534476385851, -0.9980487786612703, -0.9281856655143881, -0.9321628066064839, -1.0372416802877744, -0.886833084927726, -0.892814975891841, -0.9561851109909997, -14, -0.8969893989132542, -0.9243768003553989, -14, -0.9594272966949318, -0.8826783870256774, -0.877664124033697, -14, -0.8790429956104978, -0.9067213073064475, -0.8766474283159174] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0331  total reward: -771.8129401182775
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3304492541346324, -1.3493183943967626, -1.103863751156414, -0.8869647413498694, -0.8168816632783645, -0.8077220583796606, -0.9133891483936701, -0.7656290574687684, -0.7916342102015349, -0.8636451384169509, -14, -0.7865690794311953, -0.8122980611296392, -14, -0.835775329230576, -0.7751284765161447, -0.7696285342568903, -14, -0.7733723637439153, -0.799214436303051, -0.7703474996938119] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0332  total reward: -773.2983528795997
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2486810576634495, -1.2535082917550406, -1.0218907704961926, -0.8239054651703995, -0.763232167842975, -0.7545460813486722, -0.8653795327950365, -0.7165523323953478, -0.7226062767126448, -0.7821631925714377, -14, -0.7344104941240793, -0.7475041058082473, -14, -14, -0.7201820488176679, -0.7390705595266973, -14, -0.7211724203087856, -0.7309026292137824, -0.7197837038534344] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0333  total reward: -774.6674318568793
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1064806934634106, -1.1548712524727058, -0.9000171204705354, -0.7532082148220067, -0.6898356860941437, -0.6719232399037687, -0.7624541900539064, -0.6481931330782704, -0.6744943607277656, -0.7461574316559179, -14, -0.667045467572977, -0.6885043433407922, -14, -0.722852390594734, -0.6565493721404485, -0.6525815850404969, -14, -0.6548718476546261, -0.6741073680755887, -0.6525266448841724] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0334  total reward: -775.9176623554612
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.048587451494525, -1.096029711334959, -0.8139466753030283, -0.6897623430881562, -0.6368363945513401, -0.6171311427265986, -0.7084634462105406, -0.6087307608105883, -0.6239243859338383, -0.6849629467378956, -14, -0.6163328721709592, -0.6285173965338988, -14, -14, -0.6015819344713754, -0.6183362115000969, -14, -0.6039408584710592, -0.6103822302605088, -0.6020373655036573] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0335  total reward: -777.1538537774696
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0815609888551032, -1.0664055921162958, -0.9061340617988713, -0.7339548085380896, -0.674078317900277, -0.6632899489639501, -0.7682677372956216, -0.6321506330541975, -0.6343057959066043, -0.6628868015347451, -0.6592860631437085, -0.6492119407108451, -0.6602165591361319, -14, -14, -0.6339159418670353, -0.6451130369617365, -0.6454468551741417, -0.6363742913101721, -0.6437567260966753, -0.6346094875370599] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0336  total reward: -778.7366524999629
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6009729754555955, -1.6627595844329253, -1.3378465861437134, -1.1170856502610207, -1.0081713378419945, -0.9778292317165941, -1.1080285936303191, -0.937341182742213, -0.978005734796895, -1.0349690574285186, -1.0046115280266632, -0.9750454794943415, -1.0011570508368124, -14, -1.0356885135123066, -0.9455119718010199, -0.9555180026782231, -0.9817687391757696, -0.9540175016645829, -0.9814294649429028, -0.9506480894390098] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0337  total reward: -780.536160847545
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5222138058023547, -1.4731280124284718, -1.227450042434393, -0.9817235609385226, -0.9163646721931501, -0.9084600069113485, -1.0404756368304606, -0.8635516527604497, -0.8644325349296371, -0.9090951566383026, -0.894000512642941, -0.8793485872457637, -0.8913700566447806, -14, -14, -0.8615968665217497, -0.872972007456702, -0.8763090215843982, -0.8638897242079613, -0.8745360795135444, -0.862167164839835] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0338  total reward: -782.376290492236
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5086794291775352, -1.8690189978969767, -1.3068808169427741, -1.1119368889114771, -1.0093619273327228, -1.0002952706139043, -1.0348313801569557, -0.9751257884162507, -0.994900901594636, -1.411733749738449, -14, -0.9848999496705348, -0.984392685516246, -14, -14, -0.963657150181799, -1.0763740332362286, -14, -0.9782735362557401, -0.9859859238956743, -0.9785327781693095] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0339  total reward: -783.9147858589278
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9874034134993658, -1.0169146987019768, -0.8079153781860372, -0.6700380702607711, -0.6101904479852222, -0.5934152469309065, -0.6853281181381891, -0.5777520691768327, -0.5785636857460391, -0.6199093588925136, -0.5926907660866927, -0.5897025152089094, -0.5983457205107746, -14, -14, -0.5746910642998174, -0.5904108342728699, -0.5819833054844632, -0.576068934261566, -0.5814426827765458, -0.574838216509949] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0340  total reward: -785.1566956731498
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2059444920803322, -1.153731593165172, -0.969212836419269, -0.7497862424522329, -0.7090107441167773, -0.7173176774819717, -0.8103794733612755, -0.664401896493529, -0.6680941772648327, -0.7306986259022722, -14, -0.6787416835927188, -0.6902730443151311, -14, -14, -0.6680504371901229, -0.6797893262111321, -14, -0.6685293936317169, -0.6731834885423409, -0.6672187499221884] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0341  total reward: -786.5036123984705
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1655010473929572, -1.1948025613396298, -0.9749695234848226, -0.7795154511200982, -0.721610543225278, -0.7182393822311021, -0.7975701722675782, -0.6846839818855637, -0.6980599673145527, -0.7806047618017615, -14, -0.6985918403341297, -0.7188446609950259, -14, -0.746708894222119, -0.687642778574193, -0.6889137000621279, -14, -0.684213102654658, -0.6989207299638873, -0.6825148288271708] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0342  total reward: -788.1704547613076
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.166178837013727, -1.0003287550616076, -1.0367526865061925, -1.0356108975249423, -1.2133997636442515, -1.0203781608935194, -0.993117377152847, -1.0127626621075496, -14, -1.0049683660172664, -1.0340140521988233, -14, -1.0742461987291425, -0.9892955390140457, -0.9737656882106124, -14, -0.9865386191259221, -1.0202466395969136, -0.9843275340099668] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0343  total reward: -790.1494939378591
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6663278315902406, -1.8304891070849727, -1.3906892536935616, -1.143599115618738, -1.0541626724347062, -1.0443444732094271, -1.1661897314199046, -1.0329545442654156, -1.015183503480539, -14, -14, -1.04032624447863, -1.0906204060888984, -14, -1.100284793684618, -1.0183119910006828, -1.0072506393580418, -14, -1.0128238897468902, -14, -1.0052734883408754] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0344  total reward: -793.1063653366683
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4821530075713887, -2.1321485236006557, -1.9566286051537176, -1.9903373388447274, -1.8846743683784448, -2.0033348967653173, -1.9613051515865652, -14, -14, -2.001630898493783, -2.0830360860246597, -14, -2.0906879337806985, -1.9033998234971243, -1.8326017934989818, -14, -1.9655385339536127, -14, -1.9515979104683001] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0345  total reward: -796.3687982323693
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9817653413654568, -1.6537408857813833, -1.5118384272017829, -1.4739043941394518, -1.6748920854975262, -1.4375184499719886, -1.465531087491288, -1.6232362333673662, -14, -1.461688220798174, -1.505908117486077, -14, -1.5841623949614456, -1.4396265826078634, -1.4392931368299329, -14, -1.4340273688869023, -1.4765915750528251, -1.4298311022019738] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0346  total reward: -799.3506274672907
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1864762257869814, -1.7894573651383592, -1.6415378971907886, -1.6131548740387596, -1.816780504800787, -1.5631872604487518, -1.5848074133321641, -1.7741424703249538, -14, -1.5810710593719786, -1.618480760028043, -14, -1.7014118737528374, -1.5641218940994033, -1.5617928267892127, -14, -1.5545376586933466, -1.597851329544953, -1.5519981327194414] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0347  total reward: -802.4151647054457
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1413605540838008, -1.7387246223787904, -1.6008068809648275, -1.579089460534766, -1.782425083064806, -1.5245222353163759, -1.5442731464280848, -1.6967503825594064, -14, -1.5478267580204101, -1.6001146576756897, -14, -1.660836619839788, -1.5246179015856494, -1.5198169082316357, -14, -1.5185126516460983, -1.5492897788026763, -1.512539105435671] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0348  total reward: -805.5148893011058
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1941998600155665, -1.813992845681721, -1.6745246993712501, -1.6435128866796471, -1.82784555283159, -1.5892983008037849, -1.6277628472313486, -1.8653343750250575, -14, -1.6212594799237405, -1.6677425660270573, -14, -1.7487633476005315, -1.5991800529684148, -1.6095072170678826, -14, -1.5920006646547356, -1.6150462157754104, -1.5871854902243911] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0349  total reward: -808.5064949119408
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.010605356699397, -1.6055841118170782, -1.487654853107668, -1.4787685324111337, -1.6563525723315735, -1.4075853965971794, -1.4369471472527824, -1.5425405644927488, -14, -1.4341073729946785, -1.4756455577651844, -14, -1.5330015915338489, -1.4134409250681426, -1.398183689501333, -14, -1.408210802128748, -1.4483544224850962, -1.4044201206105216] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0350  total reward: -811.1868655613423
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6950598403934654, -1.4605867687539489, -1.3405399340978812, -1.306474583637445, -1.456709666709335, -1.308374110215779, -1.3002700757003136, -14, -14, -1.3298995244753098, -1.4007589781537648, -14, -1.4054665980431518, -1.2975040294844387, -1.279205646253856, -14, -1.293233887442909, -14, -1.282186959900266] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0351  total reward: -813.5136400134127
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8505720610940675, -1.8986072499140147, -1.3905945527931332, -1.2119528124246677, -1.112091774030467, -1.063018232192289, -1.2421790598310543, -1.0417527101944117, -1.0771085102789761, -1.2102626507532526, -14, -1.0746589606193935, -1.1038824801325304, -14, -1.1412247235850612, -1.0554951956875396, -1.0491924071933116, -14, -1.0490396335365635, -1.0745939018233208, -1.047568805816447] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0352  total reward: -815.555222055954
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7372505339899242, -1.7818700832099152, -1.3891654329888545, -1.153994662551726, -1.0604084546489234, -1.0326689082750757, -1.1992975757474604, -1.009454470586223, -1.027477126145092, -1.0954368150000242, -14, -1.0245726808376132, -1.04535820786715, -14, -14, -1.0001222136788865, -1.0224122876281685, -14, -1.0025291525537783, -1.0282722853607509, -0.9998293323469379] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0353  total reward: -817.7689290193431
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7574926293136908, -1.3805661478734128, -1.2852771212488927, -1.2904711714704404, -1.4457855681092768, -1.2049909925848679, -1.2152926452094548, -1.342113970471344, -14, -1.2346432380953714, -1.2529476350678725, -14, -14, -1.2134859783682221, -1.2540894643338347, -14, -1.2156096698534335, -1.2253393643381671, -1.2138776310421462] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0354  total reward: -821.100664099444
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3414265795196023, -2.3700652310560133, -2.2566239396693626, -2.4265897667005776, -14, -2.1489736012407192, -2.1547903371800055, -2.253130488042124, -14, -2.161933088097841, -2.2242239017936223, -14, -2.267510994287438, -2.137161526097689, -2.1055304885779913, -14, -2.133981888309061, -2.197827542999274, -2.1267440875159633] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0355  total reward: -824.8814478137085
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.317383912317472, -2.006874599628073, -1.7934699952559652, -1.6990684153014273, -14, -1.680162842441225, -1.7537937374402524, -14, -14, -1.7271723634452847, -1.8128738040603263, -14, -1.6801628424412252, -1.6857928970608076, -1.6920437862564959, -14, -1.690138279445184, -14, -1.6752532256865287] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0356  total reward: -827.6319991948405
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6441890025425494, -1.9508303301180783, -1.4698634769125667, -1.245192424345938, -1.1169660453471835, -1.1016702874067978, -1.2058478395523091, -1.1075078260422817, -1.089885558589775, -14, -14, -1.1182628598458753, -1.1892465012680073, -14, -1.1980800541013423, -1.087671822962813, -1.0696087347341212, -14, -1.0876375981747444, -14, -1.075298155445534] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0357  total reward: -829.639381158886
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5720828445605481, -1.6942996983813492, -1.270571727882492, -1.097015393307083, -0.9904663313884099, -0.953623907112279, -1.090572386715821, -0.9289805397972898, -0.9705459961259395, -1.099018970459916, -14, -0.9613620389978195, -0.9920560369073699, -14, -1.0348206985318642, -0.9444193568800088, -0.9464412806901078, -14, -0.9406743972083461, -0.9669467054957518, -0.9377732293113822] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0358  total reward: -831.5795656403034
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.653743234060766, -1.692050650082393, -1.4440790347821475, -1.1653443649689819, -1.0678518773875325, -1.0595893720004028, -1.2058168912214546, -0.9924818482353917, -1.0096534086087194, -1.0772391564094321, -14, -1.0322303188372965, -1.0533171600564097, -14, -14, -1.0122779878535957, -1.0487673340567119, -14, -1.013681636894453, -1.024473802761791, -1.011203941620058] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0359  total reward: -833.7211776361567
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0079443390684966, -2.031386977372911, -1.6088149088658752, -1.3127280738426976, -1.217770375283024, -1.1975314031389175, -1.354606880850576, -1.1530168946310977, -1.1740948468618808, -1.2941732712187681, -14, -1.1737235628773426, -1.2090190438767758, -14, -1.2518166433269937, -1.1574162814288544, -1.1544426379878, -14, -1.1527191970603372, -1.1812848014152628, -1.1491301476179057] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0360  total reward: -836.477963267615
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8996964363559339, -1.6679164721949626, -1.7093200547117096, -1.6464121792268736, -14, -1.5992947489335962, -1.6379091798640242, -1.8324064900167452, -14, -1.633973380719237, -1.6709356383013483, -14, -1.6936823407821742, -1.6183254337732058, -1.6054898490633296, -14, -1.6106810583728164, -1.6384954589488725, -1.6076554838404313] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0361  total reward: -839.4080019664916
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.5918818123681406, -1.3623424389408956, -1.4101397402826428, -1.391190980161042, -14, -1.3214121948976267, -1.3278454234988095, -1.4178906630506443, -14, -1.3511485042807485, -1.3721055512123999, -14, -14, -1.3331157463271421, -1.3480240602281435, -14, -1.3327381521235258, -1.3485823021173722, -1.3307439499430336] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0362  total reward: -842.003257118377
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.538652477347921, -1.308185226350982, -1.3528681859108234, -1.3331570541654398, -1.567947258669303, -1.277841263023631, -1.289831790176288, -1.3814260646308256, -14, -1.2914164123217364, -1.318741036549771, -14, -1.335859229392116, -1.2803540864692402, -1.2624980002153436, -14, -1.2760285101758477, -1.3064311503482604, -1.2738429569876302] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0363  total reward: -844.2001369333791
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.1168140861802505, -0.948893406935471, -0.9861960980013772, -0.9791183737346852, -1.1077806511543125, -0.9527705286911329, -0.9387210079752913, -14, -14, -0.958199289238857, -0.9924033362617252, -14, -0.9879134734124059, -0.9464023816747127, -0.9373221208578845, -14, -0.9395217830425494, -14, -0.9343818147868447] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0364  total reward: -846.0694478293917
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.0987625573955415, -0.9460634286244531, -0.9862041018356731, -0.9736854117888063, -1.1080293819990419, -0.9522123753377609, -0.9412626451022987, -14, -14, -0.9574973811791133, -0.9917231039182426, -14, -0.9948484156980276, -0.9468270503099118, -0.9393240422218971, -14, -0.9403850521292556, -14, -0.9349290812258383] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0365  total reward: -848.2735767746524
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.5824871179520013, -1.2744876629403619, -1.336894222778929, -1.3937265575579971, -1.5432668360613597, -1.3096349393153581, -1.270489506503092, -14, -14, -1.294989749194058, -1.3345901460172698, -14, -1.3423373451197536, -1.287037105188235, -1.2779680918813787, -14, -1.2755952925724983, -14, -1.2691998640348137] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0366  total reward: -851.0524766336368
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.791800336538752, -1.5312193629588127, -1.5935396800777621, -1.577332637707007, -14, -1.5243502071139758, -1.5267544612366102, -14, -14, -1.5443585291364377, -1.5975171234142047, -14, -1.6031016430369478, -1.5285211748891938, -1.5180283945026622, -14, -1.5182750444983246, -14, -1.5096999949495784] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0367  total reward: -854.3190665258871
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0248360908478005, -1.7772262443310887, -1.8500871780278556, -1.8116300277107387, -14, -1.8236462462340377, -1.762284375569541, -14, -14, -1.8017390560425888, -1.865511349481593, -14, -1.8991622814768345, -1.7806912530345334, -1.7635715690995728, -14, -1.7663674666957692, -14, -1.756889897300768] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0368  total reward: -858.2277741410783
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.56439885863959, -2.1673428306415246, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0369  total reward: -862.429384500721
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.0227280136332753, -2.2277708809428676, -2.034876816161745, -14, -2.141327554490365, -2.035884259612644, -14, -14, -2.0887571989709017, -2.160995785619622, -14, -2.2132544082969456, -2.0773085632156727, -2.0734942143386887, -14, -2.044158964231208, -14, -2.0342675290011987] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0370  total reward: -867.1333748286152
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -2.7408502669528665, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0371  total reward: -872.7485700584924
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.8457893184528866, -14, -2.9344568075537016, -2.8816229220637077, -14, -14, -2.9382896143963557, -3.031161819071068, -14, -3.0159711350742695, -2.937318339507828, -2.9173620273115315, -14, -2.8884766168077, -14, -2.8743449629243836] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0372  total reward: -877.9108740820893
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.3299369230453157, -14, -2.378519284100839, -2.3257170847431694, -14, -14, -2.3830574018278257, -2.4866895285632773, -14, -2.4713498538419256, -2.361870728829421, -2.3524143006837526, -14, -2.3334977394944216, -14, -2.316514705143962] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0373  total reward: -883.1696562707126
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.940049399036884, -14, -3.018535740681966, -2.9482019097989705, -14, -14, -2.999700793363425, -3.0907507641085368, -14, -3.1034518277772984, -3.0007231458801362, -2.9931999128967406, -14, -2.9574611079027457, -14, -2.9422674834793847] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0374  total reward: -887.9317372338293
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.8004009333853752, -1.9918521608409174, -1.8162744325422395, -14, -1.9080425148476439, -1.8267098547728686, -14, -14, -1.8817936433769347, -1.9669951212524672, -14, -1.9911979173456906, -1.8586763694863122, -1.857446037548851, -14, -1.8347313747630318, -14, -1.8220315640797633] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0375  total reward: -891.7087932339246
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.330802077107455, -1.9919492885147358, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0376  total reward: -895.745960638877
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.0646615664444723, -14, -2.0928402277787113, -2.052286716014992, -14, -14, -2.0879439272220672, -2.1455447822074287, -14, -2.164141948357164, -2.082424856216414, -2.0836479389764317, -14, -2.0532661611273038, -14, -2.0452181164377756] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0377  total reward: -899.9459732140914
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.181355547688287, -14, -2.2038280058832074, -2.1614279880009106, -14, -14, -2.2064974825167982, -2.282988416847018, -14, -2.273962193448004, -2.1980720258182282, -2.192086388069589, -14, -2.1666699756191945, -14, -2.15479445877669] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0378  total reward: -904.805183918582
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.704509864566553, -14, -2.765464334677311, -2.7121483856657034, -14, -14, -2.753307395465532, -2.8248734492085084, -14, -2.8500456667520626, -2.7555754025716563, -2.755604623303405, -14, -2.715399627122376, -14, -2.704416245713888] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0379  total reward: -910.1126296444597
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.5733024375793825, -14, -2.6476242053950356, -2.6164967155557637, -14, -14, -2.658563692342394, -2.7458618292044727, -14, -2.7456827525940417, -2.6594344437945114, -2.642591905808152, -14, -2.617472751140319, -14, -2.6030294801637996] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0380  total reward: -914.9776227337384
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.3003753474921784, -14, -2.326280417698149, -2.309510343263301, -14, -14, -2.338434452922307, -2.414710161572942, -14, -2.431882801092593, -2.3333883839616254, -2.3324085511188226, -14, -2.3047903903253055, -14, -2.2916906516992475] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0381  total reward: -919.3786584182886
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.094960588579967, -14, -2.151694574788742, -2.117399959686476, -14, -14, -2.1519727561837705, -2.2187290839051084, -14, -2.223713779705666, -2.145451411051547, -2.143585111516323, -14, -2.1203471720972313, -14, -2.109345032851087] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0382  total reward: -923.6332684326755
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.1370333592584894, -14, -2.196803319206719, -2.1728854940339057, -14, -14, -2.2028231358059234, -2.276779062187712, -14, -2.2869072620373365, -2.2042489880439167, -2.196530849540362, -14, -2.1729578432186263, -14, -2.159649425806881] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0383  total reward: -927.7339507728959
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -1.9811813342314368, -14, -2.0154769553555814, -1.9690321269617275, -14, -14, -2.008257611349589, -2.0816561059585923, -14, -2.0809307288863024, -2.0064022963448305, -1.999688727227977, -14, -1.9763574589600343, -14, -1.9636489809619562] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0384  total reward: -930.7402013835704
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -0.9333482185687344, -1.051163875069336, -1.0219882114462364, -14, -1.0634914632985926, -1.0528089785279848, -14, -14, -1.0787342980721342, -1.1308769759623212, -14, -1.1251360140374513, -1.07447559612148, -1.0674304670415147, -14, -1.0504797326796413, -14, -1.0426016297124747] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0385  total reward: -932.6828935838554
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.792989623404907, -1.6499353567066715, -14, -1.0582226504125618, -1.047417310068834, -0.9410913651525241, -1.113198718092973, -1.0497020394050807, -1.0122347242599936, -14, -14, -1.0433283444434853, -1.0961617175709466, -14, -1.093127985273645, -1.017937801759498, -1.0023779758959415, -14, -1.0179865611008363, -14, -1.0093439817162448] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0386  total reward: -934.79398092086
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0428374968555603, -1.904943657551984, -1.8792276549858968, -1.281416469135105, -1.2355464679585912, -1.3850328029617864, -1.4538882365974464, -1.2164402077081826, -1.170904439782849, -14, -14, -1.1970026380339616, -1.2373466185193498, -14, -1.2494373512284382, -1.186458087251283, -1.1824459039007622, -14, -1.1763251865163045, -14, -1.1699959718521045] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0387  total reward: -936.5625981128406
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9749927086308897, -1.0762401077779449, -0.7977225887658519, -0.6774611549967399, -0.6259659578624807, -0.6143359226092879, -0.6867642891845289, -0.6199199991685196, -0.6056351999479429, -14, -14, -0.620175860783051, -0.6547808592483841, -14, -0.6692010886176557, -0.6064360190960747, -0.5992328908969002, -14, -0.6044694085790244, -14, -0.5986212201285259] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0388  total reward: -937.5301437392924
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3901971272011565, -0.38550813975857273, -0.4531330307884941, -0.4213289047063726, -0.35907024527033493, -0.3698837984223214, -0.36796389021112097, -0.48432256780578464, -0.3671130720853298, -14, -14, -0.39527223874125994, -0.43620207254186744, -14, -0.4934957081633787, -0.3696952863040314, -0.3601042333742586, -14, -0.3756144860432279, -14, -0.3689244063232041] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0389  total reward: -938.5830124118174
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.046937124044529, -1.0278555185586737, -0.9259747179370392, -0.7764198595004884, -0.661766230775551, -0.7175754368516802, -0.7857755165978588, -0.717103840178987, -0.6979612501851291, -14, -14, -0.7198869600644775, -0.7622032747244895, -14, -0.7554517227827595, -0.7072721232324821, -0.6998913421958562, -14, -0.7010231023296079, -14, -0.6937984272546383] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0390  total reward: -940.224711015886
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6556166067508327, -1.7766342919175364, -1.3722632341144285, -1.087701176983957, -1.0263331190567508, -1.0408366240623899, -1.1187914043187699, -1.006441526442481, -0.9884886876424326, -14, -14, -1.0107442938640243, -1.0561148799104298, -14, -1.067053614937628, -0.9913679859162345, -0.97973179428028, -14, -0.9869406340847282, -14, -0.9799323732930554] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0391  total reward: -942.5028026272091
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8343631129174445, -1.4634916484265863, -1.3732984411339606, -1.371196139439306, -1.5181531042767082, -1.3055157603281375, -1.3262533179630067, -1.4917367364318743, -14, -1.3252860443940455, -1.3627902812713986, -14, -1.4215731306163057, -1.3084412112463921, -1.306599904455972, -14, -1.302053173798717, -1.3223842893747773, -1.298359817042972] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0392  total reward: -945.3741935448973
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.318550780850037, -1.7530696348933712, -1.6645583955163625, -1.7194328579237355, -1.862920199048449, -1.6030033140901523, -1.5947349678120746, -1.7108198591430068, -14, -1.6073861349324494, -1.6511010670529869, -14, -1.713483620877957, -1.5846596342760566, -1.5767207621920092, -14, -1.5761942081606946, -1.6190099541625103, -1.5730311006450692] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0393  total reward: -949.2907646675294
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.58313102162091, -2.5958118331964406, -2.4833765253455526, -2.6412156974711145, -14, -2.4100844110330915, -2.3637530633781276, -2.4685581463662234, -14, -2.380074022236807, -2.4404299722692606, -14, -2.525623809915809, -2.357277471114897, -2.3245900721130393, -14, -2.349505946137172, -2.4113511434058643, -2.3435400219869944] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0394  total reward: -953.3110050912217
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3265415507624296, -1.9411688951975061, -1.761868831288482, -1.7477561903194352, -1.8800763283818391, -1.7340318719127408, -1.7117130589989826, -14, -14, -1.7689760023317391, -1.8899554084300696, -14, -1.836753330463718, -1.711079133417242, -1.6723336192759877, -14, -1.716653008027141, -14, -1.6956503515792274] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0395  total reward: -956.8618949475288
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.707103384469315, -2.1283385233494108, -1.9898256831117427, -1.9980072969245284, -2.2206333071984727, -1.9044189270259946, -1.909298940345683, -2.0789275548257837, -14, -1.915820629480999, -1.9644090142006887, -14, -2.0481813977634213, -1.8931977954827062, -1.8762000956816132, -14, -1.882091162987158, -1.9221642633478597, -1.8785562370312345] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0396  total reward: -960.4006552667522
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.284232048028705, -1.849308515759509, -1.7382051380433379, -1.7473184471574001, -1.8940727627542213, -1.7221182878921235, -1.6766049523542956, -14, -14, -1.7286184653680616, -1.8301518904286718, -14, -1.8358992398035703, -1.6829698588540536, -1.659018582422594, -14, -1.6789747531051409, -14, -1.6625602235416888] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0397  total reward: -963.726493836853
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.342638409805051, -1.9414460293796578, -1.7626101477128924, -1.7213598594856199, -1.9540051927087856, -1.6691138336138542, -1.710250310213614, -1.8897360181061476, -14, -1.7049234328406853, -1.7559193604702632, -14, -1.8363547658333783, -1.6788513296010243, -1.6707287548420686, -14, -1.6713876674992834, -1.7151915297800302, -1.6668199876783778] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0398  total reward: -966.807135350696
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9735719095286515, -1.6358580334902235, -1.4967369302066813, -1.4617849934727716, -1.6702904360493636, -1.4304675855201179, -1.443170478796624, -1.578278818059165, -14, -1.4461617352524487, -1.4872383755015626, -14, -1.5619602852870393, -1.4247191233883802, -1.4177018124551208, -14, -1.4168205346391276, -1.4597966923588575, -1.4138215261644382] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0399  total reward: -969.3411071753485
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7727456459241484, -1.9801948478693385, -1.542794339511395, -1.312872799219236, -1.1754077748530447, -1.144734526703313, -1.275774362311217, -1.1240937224235905, -1.155589874899211, -1.3043849778194363, -14, -1.1503679088037244, -1.1868460714586635, -14, -1.269631099068638, -1.128118895478598, -1.1417790784704525, -14, -1.1233580532587004, -1.1524362184280592, -1.120150298488057] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0400  total reward: -971.6900822757466
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7655839451625173, -1.382245790205311, -1.299989098115347, -1.3125666778102503, -1.4479746229939032, -1.2442285188849058, -1.251236792192692, -1.350935291745028, -14, -1.2559930891566877, -1.2918500297548068, -14, -1.3468465911498908, -1.2382569568128101, -1.2315732176747725, -14, -1.2317683825905084, -1.2670826511336326, -1.2288248019101444] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0401  total reward: -973.766628356305
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8620537907925709, -0.8531169051388466, -1.095157983606623, -0.957225579613518, -0.8436563875713798, -0.862320763035662, -0.850335673571239, -1.114717252307671, -0.8451759815717257, -0.8733147482617436, -14, -0.880378057689884, -0.9204935593415733, -14, -1.1480674817846264, -0.8519427249017082, -0.8687637271290138, -14, -0.8526293565681499, -0.8929307634355544, -0.847721278648203] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0402  total reward: -976.2246259393361
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.20261520202591, -1.8345989588574474, -1.531642203524037, -1.6649580288501218, -1.8074717681265227, -1.6430216191409281, -1.6382104313033758, -1.901293393737404, -14, -1.6523498958919567, -1.6951834423189391, -14, -1.7553848496420776, -1.6318919820856108, -1.6125065652155406, -14, -1.6160443234220327, -1.6405458982133394, -1.614341195459746] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0403  total reward: -979.435978160726
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3023200256328034, -1.9134625398864624, -1.7839030740748572, -1.7371388754763921, -1.9983474693512293, -1.6721075480793874, -1.723476931685503, -1.9018032565885037, -14, -1.7139806384920646, -1.764412911838754, -14, -1.8202383450168622, -1.6914706591474902, -1.6794827551147218, -14, -1.6847047212340365, -1.737471109971899, -1.679710017865933] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0404  total reward: -982.6266937760187
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.172305718910602, -1.7167173432712353, -1.6126343733875785, -1.613545715332575, -1.856840806152566, -1.4829522692387203, -1.5152384090745024, -1.5964239813607808, -14, -1.5444290995408518, -1.5704019762703314, -14, -14, -1.5215262079967686, -1.5548908067332048, -14, -1.5206678782015672, -1.5319567137315322, -1.5186080672132967] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0405  total reward: -985.2717461178291
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.005437035705573, -1.9685902883114046, -1.6583761173203526, -1.3230324215193727, -1.2318228252056156, -1.2263737591300916, -1.3868784497488742, -1.1942752685912656, -1.1762874930414837, -1.2552328820016543, -14, -1.1902800806181235, -1.2264599399531946, -14, -1.2755302270690267, -1.1707542881195123, -1.1643877556451763, -14, -1.1649242022828012, -1.1936665231733041, -1.1621000725717454] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0406  total reward: -989.2110329336228
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.6912864482110255, -2.788293146773264, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0407  total reward: -992.9931494374136
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1524568776874986, -1.116282126966182, -2.018046365521362, -0.8338621797078837, -0.9362787954661881, -1.017999674706995, -1.0484990660677354, -1.231499736639732, -0.9932456774542763, -0.9914605416895064, -14, -1.0313262954915148, -1.084591592494005, -14, -1.2557478719054638, -0.9972168992015904, -0.983139578250087, -14, -0.9992469017762973, -1.0736128141040384, -0.9938233570175434] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0408  total reward: -994.9264495306171
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8050270668295845, -1.972553273923639, -1.5367839462751978, -1.3061779179009423, -1.1616375747832082, -1.1225700086471118, -1.285986993729625, -1.095835292821701, -1.1309259393351254, -1.2667601996733755, -14, -1.124768743157466, -1.1596525976174368, -14, -1.2079647407606333, -1.1076668482415528, -1.106615162294587, -14, -1.1028583104559182, -1.1329862473797974, -1.0994379134955528] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0409  total reward: -996.7845241342753
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2958923002527578, -1.3097524199687585, -1.0819420871777532, -0.8729424415034873, -0.8068206245488314, -0.7990272154545456, -0.9119639020177673, -0.7559763337309079, -0.7638307686046771, -0.8239043134280515, -14, -0.7787706819884977, -0.7932283255026742, -14, -14, -0.7623516671055923, -0.7883888921515112, -14, -0.7637169670020402, -0.7743506508155222, -0.762239310836506] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0410  total reward: -998.2795689338463
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2610754865014837, -1.328520339880319, -1.0064366898422836, -0.8535585703297407, -0.7811787395564307, -0.7569083752164736, -0.8604655676844425, -0.7417468127417683, -0.7565153179946627, -0.8616402776527433, -14, -0.7564326162554117, -0.77834889922878, -14, -0.8124068493146566, -0.7450689042450787, -0.7507611067780775, -14, -0.7409677218937991, -0.7555284759418266, -0.7390684658401047] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0411  total reward: -999.7341135198936
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1809807251178384, -1.2156980746525787, -1.0438916372262412, -0.8336831283918326, -0.7572540154036892, -0.7515426250065258, -0.8487537588631902, -0.7248243219154902, -0.7297198783543685, -0.784690190685797, -14, -0.7313643293147645, -0.7545528766627734, -14, -0.7894512851342655, -0.7205385422792389, -0.7136187126741665, -14, -0.7177670638658638, -0.7385072895482825, -0.7154761202071815] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0412  total reward: -1001.1152458742876
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1205024864157513, -1.1630840452905589, -0.9903668048560174, -0.7666508790547135, -0.7051430846897396, -0.7142339105841004, -0.818579941887221, -0.6831951228772252, -0.6749426657742971, -14, -14, -0.68758933508337, -0.7168533902103447, -14, -0.7285662077015964, -0.6770370307599433, -0.6743303203677287, -14, -0.6719843882771319, -14, -0.6675136417197961] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0413  total reward: -1002.5794252633146
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3461472443654072, -1.4781078766037026, -1.0803199979347036, -0.8920150074117354, -0.8340166788041943, -0.8273367561496019, -0.9056386342935115, -0.8193082841025799, -0.8016118278712393, -14, -14, -0.8246703086859075, -0.8644824608791678, -14, -0.8607838726614029, -0.8051303257565436, -0.7925208214504738, -14, -0.8025810686966244, -14, -0.7966657473071602] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0414  total reward: -1004.2884822593076
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.490542793750986, -1.6226202704922816, -1.27310159840287, -1.0809180347524134, -0.9667533497096222, -0.9369329093653468, -1.0660908850725996, -0.9269345112636747, -0.9374019467605462, -1.050157423602779, -14, -0.936668049223065, -0.9614433216003068, -14, -1.0215053739738784, -0.9241049963153495, -0.9192081807239887, -14, -0.9183119604036695, -0.9340906751905341, -0.9165361745424895] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0415  total reward: -1005.9134959557085
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7345946054600653, -0.7249487625111104, -0.9043822606524777, -0.8220047205465183, -0.6978045832936898, -0.7115428563997083, -0.7068548378714166, -0.9061764046708161, -0.7071016124302956, -0.7109834678245923, -14, -0.739126074319874, -0.7700369227271958, -14, -0.9763346700990907, -0.711830684881237, -0.733890840114997, -14, -0.7118186267095076, -0.7262119554145471, -0.7084775218584661] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0416  total reward: -1008.8151793405059
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3462098971552003, -2.5055540562367744, -2.0712001178438255, -2.3895440665681766, -14, -2.2378636787677726, -2.223060466467792, -2.337158619224406, -14, -2.2483848788218093, -2.316656924628008, -14, -2.31364739795366, -2.2131584434134286, -2.170071687981714, -14, -2.209240782188738, -2.2811390613605207, -2.2038788015037953] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0417  total reward: -1012.6795302684875
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5281017780599964, -2.0751664973892616, -1.8955415288885078, -1.8602496680382175, -2.0934989423480688, -1.7952872417284793, -1.8388193479124522, -2.064746082081572, -14, -1.8327694997412072, -1.8857682837541363, -14, -1.9717026775871271, -1.8062884602382892, -1.7993322453032472, -14, -1.7980447977240768, -1.829657128412198, -1.793150810137792] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0418  total reward: -1016.8463145452148
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.6337098374843495, -2.50768953627541, -14, -14, -2.436499025571631, -2.3974357753362425, -2.549967711120161, -14, -2.4157131188980436, -2.4749101391142267, -14, -2.5740156650140444, -2.3905084039195144, -2.3689840703673486, -14, -2.3784117355996357, -2.43089932433797, -2.3736334665895917] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0419  total reward: -1021.0631372959067
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5870668824594074, -2.053374191848821, -1.9270564684281866, -1.961215322762216, -2.070708089701326, -1.9101834242253903, -1.861216275482717, -14, -14, -1.9132163462920884, -2.011051381406962, -14, -2.023279663060434, -1.8669484315387774, -1.8372478617548595, -14, -1.8632157861130285, -14, -1.8478386803245108] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0420  total reward: -1024.829979167475
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7259288055579147, -2.4407621900542495, -2.065035424931603, -1.9383205744690275, -2.3808735844912317, -1.9209499482109367, -2.0253329402491063, -2.1929796447910332, -14, -1.9774638793088313, -2.0488546483762367, -14, -1.920949948210938, -1.9327630684576855, -1.9130929335388625, -14, -1.938001095889934, -2.025669072252003, -1.9295940098132691] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0421  total reward: -1028.9135855516993
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.5307260773398434, -2.2036980151603855, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0422  total reward: -1032.7772083217308
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.479128110090445, -1.7462876336925497, -1.6817964410382542, -14, -1.6921897885440247, -1.6725247686557676, -14, -14, -1.7159040183783447, -1.7908963362205417, -14, -1.7749298519473562, -1.6990413973547804, -1.6894984246655849, -14, -1.6703236537913668, -14, -1.6599247548710878] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0423  total reward: -1036.5675324534805
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.772449198367947, -2.493546694190243, -2.4859958501567854, -14, -2.316968230706982, -2.4035356634702705, -14, -14, -2.357032885287084, -2.4191697725206933, -14, -2.3169682307069825, -2.297852019240101, -2.323919969829258, -14, -2.319934987693579, -14, -2.311196021659254] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0424  total reward: -1040.1284815954396
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0416644961726846, -2.2203129760514937, -1.7757168434236337, -1.4559120466553672, -1.326497118306744, -1.311553457583118, -1.4249017495715544, -1.2673642292109952, -1.2906034675999725, -1.5041023857743543, -1.3030046082764766, -1.3089014324433144, -1.3741088556055066, -14, -1.3958012269577047, -1.2487498910498551, -1.2562996562942292, -1.2734303545398227, -1.2728008557267434, -14, -1.2630971227191015] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0425  total reward: -1042.7047680688434
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8580841585945003, -1.4780435622256105, -1.3942003433206895, -1.4062101510027203, -1.53638887234137, -1.3693297144201515, -1.332032976011078, -14, -14, -1.3753914331536041, -1.4465417916792471, -14, -1.4229660071720083, -1.3437427860518874, -1.323524972410347, -14, -1.3386422181819115, -14, -1.3275365823536798] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0426  total reward: -1045.5770956028414
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1994539426037596, -1.7783018489900124, -1.6382151418862703, -1.6203121587881153, -1.8190296031872544, -1.5604599946227358, -1.5825302623786177, -1.7258057869818753, -14, -1.5871359896586918, -1.6388748559184951, -14, -1.7045051071730366, -1.56006135215041, -1.554930397389597, -14, -1.553861600574284, -1.589658682819899, -1.5488025615877334] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0427  total reward: -1048.832525071682
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4123494884330303, -1.9609107252623905, -1.8152997405227174, -1.7824252230979358, -2.0758709747059343, -1.7416397446874714, -1.731207337399371, -1.8260829891258747, -14, -1.7474999770664537, -1.8041928679940493, -14, -1.8639939101003524, -1.717729145464143, -1.693181014564031, -14, -1.7115037932630692, -1.7556531178875134, -1.706626907253159] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0428  total reward: -1052.0450941286617
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1467548844302433, -1.6872358451405116, -1.5970576893797535, -1.6210997116285804, -1.7672565737265973, -1.5560806817176283, -1.529588974081167, -14, -14, -1.5759405070522268, -1.648242437360501, -14, -1.6329943004515945, -1.5387878280874165, -1.5195113726264302, -14, -1.5288519086573689, -14, -1.5193880424153776] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0429  total reward: -1055.3862665878346
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2425028208158713, -2.0049453847820007, -1.8074511900828822, -1.8329312547137149, -1.7424711116220002, -1.9029965660553738, -1.8248963940870186, -14, -14, -1.8678910621543883, -1.9422809301955173, -14, -1.9725300394044747, -1.7520697003620957, -1.6878791553629169, -14, -1.8344183409277022, -14, -1.8217844167575217] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0430  total reward: -1058.621719692383
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2308156749485097, -1.7483592914127286, -1.6347943137904533, -1.6513287879459408, -1.8187753279539225, -1.5881640031019417, -1.5723995956708772, -1.7029426651277337, -14, -1.5791676177760838, -1.6221727789254081, -14, -1.7247834293394784, -1.5584192546091742, -1.547561096635383, -14, -1.5510825214892885, -1.5867552129066513, -1.5475739491855198] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0431  total reward: -1062.2205745554224
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.195300100652337, -2.241859589379322, -2.1616395772286845, -2.3769102533475883, -14, -2.137769329831889, -2.054833770683836, -14, -14, -2.0989694760153457, -2.1752380915654084, -14, -2.213429254020113, -2.0804558065888, -2.069055835201915, -14, -2.0641371748283643, -14, -2.051293766404105] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0432  total reward: -1065.5340857868348
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4801830796511026, -1.2696882879162736, -1.3248854201745865, -1.3287897939321935, -1.5060955701041743, -1.3465046718257396, -1.2615090791763397, -14, -14, -1.3001303824225796, -1.3591982252919368, -14, -1.3809972069617484, -1.2809491818117362, -1.268015716717181, -14, -1.2719012775132612, -14, -1.2622174650082785] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 0433  total reward: -1067.5970144403589
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.318325762212621, -1.449371314076075, -1.1035753144906388, -0.8914399551496869, -0.836539259612465, -0.8426496357432371, -0.9016750454432612, -14, -0.7911005072362738, -14, -14, -0.8302505414065394, -0.871290229287889, -14, -14, -0.8157830525609517, -0.8126308674581352, -14, -0.8075261017465265, -14, -0.8014195743477536] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 0434  total reward: -1069.3220063421286
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6362391467611235, -1.572710103955273, -1.4177042033725225, -1.0360385184645544, -0.9873886716913366, -1.0454023514137418, -1.1569379607970525, -0.9612891715999363, -0.9387168746729992, -14, -14, -0.9635234903942815, -1.0066795997215638, -14, -1.0060423761580863, -0.9468486800620912, -0.9432848141220171, -14, -0.9404780744613194, -14, -0.9338913945335133] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0435  total reward: -1071.0264812886378
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6983073917049947, -1.3101549384899651, -0.9095679553974848, -0.7798599520429069, -0.8120767136011192, -0.8092082537806919, -0.9579983341733677, -0.802569390553418, -0.7726953011739969, -14, -14, -0.79310015263472, -0.8287920350550365, -14, -0.835878349122635, -0.7818265059904095, -0.7778268929198697, -14, -0.7765388188187697, -14, -0.7705835519756247] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0436  total reward: -1072.4104806895464
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9946874005244369, -1.162258665177011, -0.8182479149519611, -0.6913254220751365, -0.637576387982838, -0.6298339699620137, -0.673662034444219, -0.6276687301357734, -0.6195031692193418, -14, -14, -0.6360252727390099, -0.6697180869441131, -14, -0.666299836859928, -0.6180221456117843, -0.6063532080311957, -14, -0.6186878242945977, -14, -0.6134158489330179] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0437  total reward: -1073.7066544144805
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2037773764409256, -1.2512790915586107, -0.9437024431009735, -0.7929558313709795, -0.7303944991687839, -0.7090598026949292, -0.8062427072314228, -0.6834861525761629, -0.7108182431891719, -0.8057692259057267, -14, -0.705274174618293, -0.7257534281063291, -14, -0.7491807104362482, -0.694731810286561, -0.6957867969515362, -14, -0.6917104672233679, -0.7098603942841686, -0.6898205169029357] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0438  total reward: -1075.4733194337543
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.2807984211162209, -1.1020759814130934, -1.1384598351616833, -1.140423938583446, -1.3705000389037394, -1.0283489581536984, -1.1024126936830507, -1.087971558362822, -14, -1.0980384155300207, -1.1132003459331186, -14, -14, -1.0885623357400447, -1.090858422533415, -14, -1.0835617713613634, -1.089377853802415, -1.0831788666976774] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0439  total reward: -1077.6843556053122
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0479770161736637, -2.02906304457418, -1.6681124709427526, -1.3417963493010694, -1.2524207419017832, -1.243331711551875, -1.3989531737206031, -1.1831816894991447, -1.215160688444925, -1.3152996892038566, -14, -1.2107284371431042, -1.2501825384978194, -14, -1.3056158083839577, -1.1894670563095957, -1.1783814490320452, -14, -1.1865429757755437, -1.2213597846009652, -1.182687213404064] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0440  total reward: -1080.7703779183787
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8569115959163174, -2.058870315754611, -1.9998910312988072, -2.1768827735205067, -2.2090929803406563, -1.992356019705326, -1.9106294741529883, -14, -14, -1.9594101817639298, -2.037956575219833, -14, -2.0630099382508615, -1.9321165664576279, -1.9110422190408962, -14, -1.9201681315841932, -14, -1.9076408640345281] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0441  total reward: -1084.4004276739247
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.47993296260812, -1.9178463066422837, -1.806240179616427, -1.8553775728502107, -1.996940435279025, -1.7845103243803084, -1.7312879561993753, -14, -14, -1.777571332300656, -1.863708539392944, -14, -1.8757791424904475, -1.7450605713105887, -1.7237903683920326, -14, -1.7365633796597393, -14, -1.7224088915113296] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0442  total reward: -1087.6016015463592
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.988751332573838, -1.7217734096520854, -1.5429249189241268, -1.5021706318551398, -1.6803608127271399, -1.5037697368245249, -1.4990981357425814, -14, -14, -1.5405515617760541, -1.6340894926147258, -14, -1.607549935888827, -1.495394935855153, -1.4708164076830492, -14, -1.493648498876265, -14, -1.4787649809233454] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0443  total reward: -1090.8319630208177
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.367071937516648, -2.07027980247491, -1.8698228638976058, -1.7816928480797305, -2.097740459828963, -1.7492836470566744, -1.8062204234676889, -2.020105688960511, -14, -1.7999786701142837, -1.8597208817099882, -14, -1.903623920409406, -1.772888195384288, -1.759210461100783, -14, -1.7662262669261442, -1.7980540689709206, -1.759545066775377] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0444  total reward: -1094.3734561850533
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5635232497589504, -2.109071262427, -1.904095259207985, -1.8549510455838187, -2.182374517248951, -1.782881265491308, -1.795880746352006, -1.974087470788147, -14, -1.8312201621031996, -1.862174286526706, -14, -14, -1.7943902098690934, -1.8430616102832273, -14, -1.7945818581160942, -1.8160874274971617, -1.7922095171788837] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0445  total reward: -1097.6953444391931
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.132600864568198, -1.770092905113644, -1.6349271071753622, -1.5905559801706441, -1.8355290951629364, -1.542481968431028, -1.5711905880450985, -1.7268652196339345, -14, -1.5742830210436625, -1.6223212884009035, -14, -1.665949849409561, -1.5503301590651177, -1.5415775029113366, -14, -1.5434002336950403, -1.580723293472402, -1.5390069886485338] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0446  total reward: -1100.659741593786
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.017509667318355, -1.6398586732849663, -1.5151602884459103, -1.4865080133621895, -1.7058901487904263, -1.4316816768803788, -1.4512233185011858, -1.5857405926247603, -14, -1.4548528233575206, -1.5002321260092455, -14, -1.5340815484635546, -1.4356590327047292, -1.42579886212147, -14, -1.430442823013172, -1.4617953829195547, -1.4253901659444264] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0447  total reward: -1103.3729218516469
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.892061339766155, -1.4733600780504235, -1.3637663724624958, -1.3744928535610252, -1.527880358364135, -1.3061609589737495, -1.3101961977789611, -1.4033162687204648, -14, -1.3156660516753365, -1.3525194844045478, -14, -1.4102395660179543, -1.2966374661290063, -1.2831123777286086, -14, -1.2906253416338382, -1.3257704321942543, -1.2877900919162604] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0448  total reward: -1105.7998650760346
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9114259076483033, -2.1034166005078427, -1.5547126261556543, -1.2994811726492252, -1.1994724954771327, -1.1799484082025835, -1.323186250767958, -1.1591827613706713, -1.1644535726544938, -14, -14, -1.1874334408730927, -1.2554180759904208, -14, -1.2510656469024393, -1.157974027254982, -1.1460962708488416, -14, -1.154985323897942, -14, -1.1438308466593137] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0449  total reward: -1108.2210364255154
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7724467718941899, -1.477876170868181, -1.3375108273217666, -1.3162689712529014, -1.4776259033621417, -1.301993721365928, -1.2967768120304164, -14, -14, -1.3236518648440023, -1.391378692279108, -14, -1.402128292813271, -1.2938077641114063, -1.2801546922421065, -14, -1.2877241241251438, -14, -1.2773405028213562] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0450  total reward: -1110.9049815365133
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9061717267759903, -1.587843025438533, -1.4730396300386357, -1.4556251907432154, -1.6264497711982655, -1.4518629922811872, -1.423732325387937, -14, -14, -1.457751448614827, -1.5432583272882292, -14, -1.5657158752947327, -1.4253933304640345, -1.4093490150865773, -14, -1.4216395470563967, -14, -1.4066046081767327] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0451  total reward: -1113.9281238814547
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.299459642173283, -1.8103729756197589, -1.6976740703153592, -1.7207388466934361, -1.883300653565135, -1.668430881061189, -1.6245299063556247, -14, -14, -1.6707440092045431, -1.7520441976670476, -14, -1.7475771558879318, -1.6373939463418383, -1.6178530141593215, -14, -1.6293466898183782, -14, -1.6165377367645322] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0452  total reward: -1116.8645445475668
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7739513243121683, -1.4887557669218348, -1.3791071968185213, -1.3593961399595984, -1.4877986745848224, -1.3341835247717146, -1.3420929801849457, -14, -14, -1.3687112255554508, -1.4476455032131672, -14, -1.4298472789921535, -1.3334140674854202, -1.313788775333304, -14, -1.3333145127554578, -14, -1.319882929347534] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0453  total reward: -1119.3588757511675
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9441913142779974, -2.080953505416404, -1.7138467388181786, -1.374112463009522, -1.2456559333347452, -1.2366491892430773, -1.3705297114911121, -1.1892525350857015, -1.204729971579248, -1.3578726723071475, -14, -1.2072979343777512, -1.2419319695110147, -14, -1.294343273820685, -1.190259727483604, -1.1897817555614802, -14, -1.1837451165554178, -1.1966525070279481, -1.1805424282675563] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0454  total reward: -1121.7168192864265
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9866762901770618, -2.0786403293774356, -1.7128610923414047, -1.362772232884886, -1.245284429115215, -1.2388657125632125, -1.3776281400693569, -1.1706655334327154, -1.2097118605897086, -1.3427200932417271, -14, -1.202141197906656, -1.2356649081623075, -14, -1.2786769394904551, -1.1854803256795474, -1.1799376749072565, -14, -1.1803960237536066, -1.213200535768097, -1.17740110699139] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0455  total reward: -1124.5101607636439
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9359188596053474, -1.65080448004378, -1.7080659555221245, -1.7154986633382947, -14, -1.569138780310367, -1.6246080052381924, -1.6480468775386976, -14, -1.6453677799727533, -1.6720905386549456, -14, -14, -1.6280970460470814, -1.6337876823264659, -14, -1.6247523622236217, -1.643840733811946, -1.6226759437845997] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0456  total reward: -1126.747120305011
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1671115441883386, -1.1882798236398286, -0.92928168031082, -0.7681257027451239, -0.7082992506573457, -0.6913180023771652, -0.7901418601274673, -0.6737039084287622, -0.6799567848050166, -0.7490897106049591, -14, -0.6825475579567674, -0.7033449422857251, -14, -0.7265357252258139, -0.672699065956452, -0.672225904699337, -14, -0.6699062843934714, -0.6842958181001904, -0.6678207610568161] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0457  total reward: -1127.7551761566788
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.34274590094666313, -0.3408120288561547, -0.4311200048449075, -0.3848290148840742, -0.3400845686499973, -0.34360953121748716, -0.3437366136249756, -0.44368337820638376, -0.33957656306850986, -0.3560322958437927, -14, -0.35353639565962053, -0.3690585161912173, -14, -0.4642795609544689, -0.3411674798284155, -0.3390317781106413, -14, -0.3416959523657561, -0.3628482932303208, -0.3402350906110393] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0458  total reward: -1128.3661003044247
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.2834175755844028, -0.28044616579766435, -0.3385145725354295, -0.3141546874803599, -0.2669952903049464, -0.2723070436388404, -0.27219446604892744, -0.34829757847057474, -0.2706864536529801, -14, -14, -0.29072829168160347, -0.3189165907773928, -14, -0.36692281133887655, -0.27383523619617495, -0.2704090353144671, -14, -0.27632301724013814, -14, -0.27189236963507935] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0459  total reward: -1129.0623583916597
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6469303008893941, -0.6387814883213543, -0.5639744272729703, -0.4816928173966085, -0.40970581380552545, -0.4404310733161389, -0.4861164487029148, -0.44351613073477875, -0.4321865515294769, -14, -14, -0.4451908008249288, -0.47065385436097984, -14, -0.4687511310915828, -0.43774161625448255, -0.4330990397083065, -14, -0.43354773938195795, -14, -0.42926279693011077] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0460  total reward: -1129.8765405120034
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6682282486938739, -0.7356996338430353, -0.5792578397038092, -0.45409567935730055, -0.42311342272100927, -0.4310384492434567, -0.46042862498547793, -0.41508670801333014, -0.4077856976199398, -14, -14, -0.41717575409919244, -0.43731335475574457, -14, -0.43886254796712787, -0.4090849947978627, -0.40402069369930727, -14, -0.40783752873809465, -14, -0.40447630653824973] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0461  total reward: -1130.8228405102486
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1662151238073892, -0.8546130689734976, -0.6439802796090426, -0.5491967681703469, -0.5694644646760458, -0.5743928133825906, -0.6591154943238493, -0.570229050093997, -0.5464315647297088, -0.5612127397546348, -14, -0.5525329161096844, -0.5677821929149981, -14, -0.6014971204707539, -0.5458609773518668, -0.5367844027998316, -14, -0.5435816618130854, -0.5557090659349837, -0.5422793045460282] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0462  total reward: -1132.019900695641
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0978723949674043, -1.1818378491722958, -0.9563506574179286, -0.7367930389733053, -0.6915037812278887, -0.7119293515141702, -0.7574265531377585, -0.6782578997906665, -0.6653616017659691, -14, -14, -0.6796633237550626, -0.7097470097950916, -14, -0.716324966421416, -0.6681201361863436, -0.6604987454313179, -14, -0.6651873615884355, -14, -0.6602757825923651] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0463  total reward: -1133.4158802510215
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2258970933925137, -1.3105228425851116, -1.049164646501214, -0.8165888676772372, -0.7701468031011864, -0.7898879554094598, -0.8418263281138931, -0.7620392338446689, -0.7397677687386901, -14, -14, -0.7608295063061127, -0.7988827925997419, -14, -0.8022454323696663, -0.744705177683024, -0.734728788055793, -14, -0.7417613609846745, -14, -0.735703772787944] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0464  total reward: -1135.0901423797507
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6117261104432317, -1.6681421518616892, -1.3197833816308893, -1.0758819519898264, -0.9934031710267902, -0.978981749784852, -1.0954855598094175, -0.9410674450403297, -0.9617421090819009, -1.07619438406246, -14, -0.962038645419407, -0.9906004305565715, -14, -1.0275754852337153, -0.9465689396058673, -0.9491378867872939, -14, -0.9420598094924074, -0.9614421410825975, -0.9395333406735449] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0465  total reward: -1137.0888995652456
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8324432750255215, -1.8316757239270671, -1.5345153280165469, -1.2161615674515185, -1.123826598443568, -1.1189688868645273, -1.2628724072208464, -1.0617030787541142, -1.0815772567437865, -1.177878395097764, -14, -1.0830229664867683, -1.1169412868017206, -14, -1.147256145217106, -1.0667617151793527, -1.0592434750165753, -14, -1.0625446302381745, -1.0921029054948839, -1.0592238448213946] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0466  total reward: -1139.1610233232009
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7500034714161732, -1.7591995097353479, -1.4396722515457954, -1.16638309649696, -1.0746176285030447, -1.0582960347495316, -1.2071872630155915, -1.0155677215939023, -1.0355532674428796, -1.1067487716632527, -14, -1.039625708337647, -1.0743761220049133, -14, -1.102949533345982, -1.0192103740927063, -1.0131486234227918, -14, -1.015900341831043, -1.0526191336096964, -1.0128999131337775] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0467  total reward: -1141.7453025259424
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4557318903139356, -1.755543580872113, -1.6709788697787873, -1.7826265418654665, -1.93995768649911, -1.5881467172763408, -1.5910311694798598, -1.621692382678724, -14, -1.598777257736345, -1.6464987813125789, -14, -1.668036007321885, -1.5756529573759304, -1.5512844537700317, -14, -1.5764610792691947, -1.6432407921771304, -1.5713792896077459] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0468  total reward: -1144.449350226613
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8736588927827007, -2.103818117813928, -1.5836999613718856, -1.3020783160844267, -1.2034664785387506, -1.1986136679725634, -1.303947953650734, -1.2128670583066141, -1.155301379497441, -14, -14, -1.1922556826746855, -1.2485751424875453, -14, -1.2660027933471225, -1.1660140747251677, -1.1479156287448609, -14, -1.1611606838295705, -14, -1.15276324690065] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0469  total reward: -1146.901725742392
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8061978165798884, -1.612275366315396, -1.404509779224402, -1.3124248371928788, -1.6609385135290793, -1.2947769231053994, -1.3816729838377328, -1.4112287596869344, -14, -1.3380387257732105, -1.3991267909792844, -14, -1.2947769231053996, -1.2953748801494926, -1.2912313893034053, -14, -1.3132918160802758, -1.430932456216401, -1.3044598870341073] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0470  total reward: -1149.1822302552187
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6160342658199636, -1.8529847343542913, -1.3187560138029455, -1.1429299563926383, -1.0349520653040574, -1.0052278073043601, -1.135000127294595, -1.0130474906105469, -1.0005124020461702, -14, -14, -1.0234987361858807, -1.0808285339944839, -14, -1.0817415389625424, -1.0017002259294474, -0.9871565137494726, -14, -0.9993724976749233, -14, -0.9892731235233676] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0471  total reward: -1151.0328621683695
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4724180872517407, -1.5623518876832292, -1.1802329736387205, -1.0029583380622276, -0.9131188062257976, -0.8831015627492749, -1.006964493020073, -0.8615976481238632, -0.8868133464607508, -1.0188335707501155, -14, -0.8827504859023066, -0.9066395541631321, -14, -0.946566980596698, -0.8702761777508408, -0.8710106621183894, -14, -0.8653536056210915, -0.8807651615068786, -0.8634753994013586] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0472  total reward: -1152.67568127316
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3459859389488469, -1.3277013513143794, -1.1103599929924637, -0.8895185346356151, -0.8279178888759466, -0.8228492334818865, -0.9425907264888364, -0.7717316174510203, -0.7804745983230726, -0.8367328864803185, -14, -0.7956544013746084, -0.8099801151845438, -14, -14, -0.7817355696156568, -0.8016554748162915, -14, -0.7827672441726556, -0.79270687403128, -0.781221456666659] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0473  total reward: -1154.2143318619965
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2908124683697952, -1.3789859430721343, -1.0477220611640792, -0.8991628755463408, -0.8111643595491004, -0.7813388834792315, -0.8982974171880478, -0.771015484229609, -0.7851546564758956, -0.854526926620626, -14, -0.7854917015586249, -0.8111930128368807, -14, -0.8462758935956365, -0.7723171209384386, -0.7687741897490284, -14, -0.769545739032438, -0.7878280386078416, -0.7669189713855143] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0474  total reward: -1155.796824938969
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3360435588990032, -1.479399492362983, -1.1108636686967694, -0.9637971484811817, -0.8596632420047818, -0.8275585194208812, -0.9427898304143401, -0.8077176686453883, -0.845386280016277, -0.9598889527283444, -14, -0.8377097351088185, -0.8688904015409156, -14, -0.9046823960598875, -0.8212471008570315, -0.8232984649673939, -14, -0.8193718838133565, -0.8336904436903815, -0.8155741055868873] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0475  total reward: -1158.062187562592
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.106146793890078, -1.7890994748334315, -1.559399088230489, -1.4844367055599108, -1.820937447020698, -1.4703253076380038, -1.775542378802375, -1.6093043698586356, -14, -1.4972470330085652, -1.5431014503514586, -14, -14, -1.4523243291018741, -1.4621163840532572, -14, -1.46937644750446, -1.5845801980877525, -1.4576449549777686] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0476  total reward: -1160.4853654917474
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.692881181897846, -1.6362921791390717, -1.406713714663622, -1.1192110515985496, -1.033484599777063, -1.0237663430271, -1.185538280323072, -0.9642741067041647, -0.967010561691128, -1.0082245783198125, -1.0024466111268, -0.9906444515446927, -1.0076818281754778, -14, -14, -0.9690694578526198, -0.9886592588283009, -0.9850617318935694, -0.9737618399966985, -0.9858359189520497, -0.9708536000533948] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0477  total reward: -1162.2097827954
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2752465254597056, -1.3442756461614522, -1.030984321559382, -0.8955546600351821, -0.8051608905843143, -0.7713785558789615, -0.8809515537351066, -0.7464942554462344, -0.7866220554460831, -0.8480826824124758, -0.8049331686087944, -0.7792936293336622, -0.7978167583294024, -14, -0.8384355382270176, -0.7551891565654894, -0.7630976975916942, -0.7824967313779427, -0.762175185758191, -0.7814858949839728, -0.7601431969484946] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0478  total reward: -1163.718058537408
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2629108111663327, -1.3298170049287683, -1.0747887718476583, -0.8943828330919906, -0.8064027553159336, -0.7849799011801297, -0.9016734016649898, -0.7652097556164423, -0.7683981198511746, -0.8216269637518779, -0.7882919954768853, -0.7801162051328424, -0.7921627164261621, -14, -14, -0.7623733620818056, -0.7790301594229839, -0.7723243723075865, -0.7638146655960932, -0.769613131393768, -0.761781486561787] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0479  total reward: -1165.2934511904084
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4241378331142638, -1.3891189828626151, -1.1718097163772405, -0.9354280236217867, -0.8654864588164293, -0.8566337384785939, -0.9857233238033088, -0.8095749540418273, -0.8111175612480539, -0.8526325078204733, -0.8417110727790769, -0.8281523833671733, -0.8388583252648302, -14, -14, -0.81305552471997, -0.8244476058435851, -0.824802549914105, -0.8152158969600691, -0.8228197533720797, -0.8136111664385501] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0480  total reward: -1166.7964311825704
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0586648431937793, -1.2928835912989276, -0.934199668328218, -0.7977355619522066, -0.7171068234428589, -0.7073384911733126, -0.736147184575048, -0.6801426898718697, -0.7234601209420912, -0.9468484872873226, -0.6962599310914572, -0.7019328832851085, -0.7075269804768782, -14, -0.7852119528378669, -0.6941878390935468, -0.7201194723451435, -0.6895466664941937, -0.6940649736600096, -0.6940979663974807, -0.6934050381202814] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0481  total reward: -1167.9618290632106
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8393631396386799, -0.8295428773971225, -0.6825178177603907, -0.5626527336247272, -0.5160823126396898, -0.5029343789960259, -0.5879989300354467, -0.48092763125684646, -0.48319035440551494, -0.5141740162104748, -0.4980087872388239, -0.4951296413156181, -0.501037188795304, -14, -14, -0.48470537233410904, -0.49664105713078543, -0.49017099470617315, -0.48598142686232665, -0.49019059081144567, -0.4852551907681753] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0482  total reward: -1168.8317867688206
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6631148290151079, -0.6649590797725147, -0.5646548940755175, -0.44978857027474567, -0.412749018123292, -0.4093812467464032, -0.4549983790427209, -0.39032948944901064, -0.39581459776673494, -0.4181761759359447, -0.40697156940850465, -0.39752891525042594, -0.4073305519865038, -14, -0.4217699846082641, -0.3866893615472532, -0.3907469877587781, -0.3975609739143267, -0.39040732331061667, -0.39755195086537204, -0.3890300743532636] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0483  total reward: -1169.5389980710927
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5510279100917593, -0.570725074708012, -0.4340970621989609, -0.37038175796425393, -0.339370885746878, -0.3276397628332809, -0.3769321610443631, -0.3206918037184634, -0.32917435673324313, -0.36147643608996216, -14, -0.3284703065442461, -0.33936415662553726, -14, -0.35363140070142657, -0.32278057439085495, -0.32137463604954486, -14, -0.32161172316782227, -0.3299636544568857, -0.3205219407247612] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0484  total reward: -1170.1862595633306
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5566050798077065, -0.5732513737945855, -0.4614744913415812, -0.37640917266315804, -0.34579461834054026, -0.3402152497930134, -0.3840646764251339, -0.33152409847651526, -0.3323643100118877, -0.3712743233510927, -14, -0.33358754989186323, -0.34200022140700187, -14, -0.35846025040307644, -0.3294389527054963, -0.3285405546082002, -14, -0.3273045663468032, -0.33305870307994134, -0.3267395515131817] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0485  total reward: -1171.0236678554957
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7793402154266375, -0.9756756172162937, -0.6828954790359534, -0.5806900834463441, -0.5257538275229175, -0.5219677858364036, -0.5362068437679606, -0.5162930861706001, -0.5217690445097951, -0.7629740191617612, -14, -0.5147186144628598, -0.5175438558404148, -14, -0.5738914096797396, -0.5110961939600124, -0.549175996688656, -14, -0.5105953945029916, -0.5098668716786057, -0.5106687406519804] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0486  total reward: -1171.97888835607
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7812052468121686, -0.765892249595538, -0.6202172811909754, -0.520781323380683, -0.47486377551607395, -0.4581357593460247, -0.5874840774276483, -0.4432818497685958, -0.46508406467715846, -14, -14, -0.4520954421513202, -0.4559537571856956, -14, -0.49970586364327807, -0.447927745214636, -14, -14, -0.44534525952259474, -0.4339406422098472, -0.4453536288957097] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0487  total reward: -1173.080230571048
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1872994646711963, -1.1365055183366937, -0.9476164900950517, -0.7352714548256243, -0.7053915294719004, -0.7201530864748873, -0.7806871740739018, -0.6799774210570257, -0.6775514983779602, -0.7396477771190544, -14, -0.6807379301607813, -0.6993437916336508, -14, -0.7325555109588363, -0.6724567218895255, -0.6702738124841157, -14, -0.6691617953391774, -0.6803774681718501, -0.6674015727682251] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0488  total reward: -1174.4745028863965
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.251143180328267, -1.3053183583790493, -1.011252212605531, -0.8353235237897175, -0.768745787006805, -0.7524749030219281, -0.8468081171678294, -0.7253132474105248, -0.7458224350917622, -0.8348909959764517, -14, -0.7414394460583961, -0.7620414040263818, -14, -0.7938880297767185, -0.7321913356869426, -0.7303080358232161, -14, -0.7289087558967412, -0.7453416106689223, -0.7268707425801446] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0489  total reward: -1175.9896595941682
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3317634271717789, -1.411099204615478, -1.091627687598076, -0.8992898693336437, -0.8319859198312117, -0.8198604466117909, -0.9136773077214633, -0.7918739477034354, -0.8052578847635438, -0.9144909677458647, -14, -0.8077286390399582, -0.820349608232213, -14, -14, -0.7884640281488828, -0.8356538570593758, -14, -0.7912626355849943, -0.7985136317715736, -0.7898434603611032] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0490  total reward: -1177.93277107321
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9702107679914227, -1.8893323063033873, -1.7837505678833103, -1.3249758251509074, -1.2271727824625542, -1.2662516139222881, -1.405936431902055, -1.1423338456307628, -1.1479075278824984, -1.2016749130666313, -1.1858531804626444, -1.1730763111423674, -1.1881439053325735, -14, -14, -1.1521074657389023, -1.1691917906024556, -1.1663755214880172, -1.1569586116320774, -1.165811166212311, -1.1546474508930418] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0491  total reward: -1179.8474779471271
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3207341858314103, -1.3846528167846461, -1.0391901122448404, -0.9020369184979636, -0.818258246878626, -0.7841363726578201, -0.8919556221281678, -0.7653118762217326, -0.7925219351754613, -0.862024628960302, -0.8098713324299105, -0.7929383255861624, -0.8128845740743252, -14, -0.8441246980934376, -0.7660481860049181, -0.7793385025030279, -0.7893075005728153, -0.7750401483426704, -0.7844876496342905, -0.7723730282862898] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0492  total reward: -1181.5249451087143
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6305419428069843, -1.5629081019483584, -1.303974799777901, -1.0350995942456782, -0.9701735505173993, -0.965277473582874, -1.1021563162815586, -0.9079623153627656, -0.9094638491084203, -0.9615359835529184, -0.9374342393482873, -0.9312454971978585, -0.9423470024496045, -14, -14, -0.9110409946009218, -0.929344737385835, -0.9227308466983295, -0.9134561074352828, -0.921195524198706, -0.9121552853652583] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0493  total reward: -1183.192239247005
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3112827947617869, -1.313187890042467, -1.0353150876783253, -0.8623461672672159, -0.803371713715617, -0.7851026576707302, -0.874582549826118, -0.7613611544141381, -0.7759999940088862, -0.8349781867269006, -0.7948060138294456, -0.7767337108443629, -0.7958342469894417, -14, -0.8394073018789883, -0.7531166260034178, -0.76678396847712, -0.7749649383799043, -0.762135778699595, -0.7736851610261276, -0.7593318229281788] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0494  total reward: -1184.6990188585278
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2905820714671885, -1.2897779994045522, -1.0923093971760915, -0.8659224033801443, -0.7991319920075086, -0.7962271158617376, -0.8983595165126587, -0.758171862390295, -0.769532615262266, -0.8196413254549678, -14, -0.7709557335986991, -0.7950740702131182, -14, -0.8225880537656911, -0.7585913538864295, -0.7500850622673558, -14, -0.7558506621545905, -0.7803546901290708, -0.7536629855191757] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0495  total reward: -1186.1157978485162
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1051157349425933, -1.2362001019888367, -0.9148043601931297, -0.7449413888655894, -0.6958198466279136, -0.6969641456835108, -0.7459780369460348, -0.681852353913934, -0.6727657455587516, -14, -14, -0.6925729383218044, -0.730286193721731, -14, -0.7213358758817846, -0.6728834543799824, -0.6618972932375524, -14, -0.6724537702187193, -14, -0.6666939277210023] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0496  total reward: -1187.4524077309763
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1432946441440341, -1.1892687239229134, -0.9590701012259812, -0.7732869380357495, -0.7127087008911783, -0.706619917318064, -0.7844166189853082, -0.6696444431174385, -0.6960703607966569, -0.7817195565764716, -14, -0.6897733016565898, -0.7103545376704528, -14, -0.7401663173604129, -0.6792513778924133, -0.6789395518128952, -14, -0.6767181567739401, -0.6954435999250748, -0.6747125892225647] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0497  total reward: -1188.8840455021436
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3574304781643434, -1.3186000393391746, -1.091744924496139, -0.8781474756182054, -0.8120753808843647, -0.7990476526516066, -0.9437370110502897, -0.7612530276609185, -0.7645444956039343, -0.8148089404024889, -14, -0.7785152824740912, -0.794447028887053, -14, -14, -0.7629249080147552, -0.7741197197671746, -14, -0.7637270889916024, -0.7801492653054783, -0.7619933280498806] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0498  total reward: -1190.3887077331142
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2523961869642264, -1.2791374454857143, -1.0408879163901623, -0.8423267529890424, -0.7841207278413393, -0.7793099255108784, -0.8623013068251372, -0.7621488359068673, -0.755193639051865, -0.8355849684256814, -14, -0.7604306768846696, -0.7780800242241454, -14, -0.8282071323492413, -0.7496260364265812, -0.7510828424649788, -14, -0.7440880498282029, -0.7592105565063278, -0.7434092033096088] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0499  total reward: -1191.9531113356006
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4099582749265893, -1.4310025325172013, -1.184204228681672, -0.9355606208693122, -0.8686216778912622, -0.869588180420217, -0.9628088075734632, -0.8259922175496679, -0.8374153213015572, -0.9307340303825643, -14, -0.8393859561322562, -0.8623103140567134, -14, -0.8947134998417071, -0.8274248729591844, -0.8244674887811533, -14, -0.8227759625578864, -0.8370020669244645, -0.8209943991768192] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0500  total reward: -1193.4750902983092
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1928905341034095, -1.204136568938655, -0.9982827482963116, -0.7985059989287814, -0.7412480723314464, -0.738340405713806, -0.8234649181765084, -0.7104571719244659, -0.7143084555371109, -0.7738269906031067, -14, -0.7174511245163665, -0.7395472274298531, -14, -0.7727950978880405, -0.7063792297355649, -0.702780392138633, -14, -0.7030159013385412, -0.7192256341859729, -0.7009845635318444] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0501  total reward: -1194.9272065049531
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3015832888040164, -1.4548588890630405, -1.0380013115218356, -0.9421365919053334, -0.8026831450440536, -0.7529002370693071, -0.9175912788740758, -0.7486992527483697, -0.7901620935052919, -0.8710590927473614, -14, -0.7691838135568995, -0.7957704433930416, -14, -0.7486992527483699, -0.7526299347347974, -0.7458358668775004, -14, -0.7542604859460735, -0.7877413320958114, -0.7511316431119668] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0502  total reward: -1196.4198031314436
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.28749250731346, -1.4617515872097182, -1.0501039564477226, -0.921028990510761, -0.7942959864950849, -0.7536750059794171, -0.9398601002649525, -0.7491689607470385, -0.7852854263875182, -14, -14, -0.7705214518899226, -0.808315616293966, -14, -0.7491689607470384, -0.7520887331944068, -0.752669701719158, -14, -0.7530887724242812, -14, -0.7467607596131087] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0503  total reward: -1198.0209525140192
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8236113951737958, -1.4340108334001163, -1.0219097480901955, -0.8525454833476829, -0.8948083139543539, -0.9219999278688865, -1.0066950148244116, -0.9062351817044282, -0.8539076595759428, -14, -14, -0.8784319871210379, -0.9184232069822331, -14, -0.9267277036119824, -0.8663503967342261, -0.855985561365973, -14, -0.8613859670426306, -14, -0.8543886229624973] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0504  total reward: -1200.3666081127212
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.3433348905587663, -1.4783662440369938, -1.5647044798811478, -1.725609982916854, -1.5347526856908684, -1.4977806315739715, -14, -14, -1.524713660141163, -1.5718766075514465, -14, -1.589232004358365, -1.5028065055679156, -1.4658848492345855, -14, -1.5005010336607445, -14, -1.4931101153544115] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0505  total reward: -1202.468951867077
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2476095545267687, -1.3785597876823816, -1.0615711412529678, -0.8393308244744653, -0.7911971236940512, -0.8077198786500855, -0.8446052478232253, -0.7892931978440975, -0.7611766607295496, -14, -14, -0.7880403571632268, -0.8334335591329771, -14, -0.8218711432268604, -0.7658141290168294, -0.7506046619534913, -14, -0.7664781955757617, -14, -0.7590088637968547] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0506  total reward: -1203.8745583133498
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1212591093273714, -1.174094852078843, -0.8873263598856831, -0.7561349305722098, -0.6926810877018248, -0.6697672257429221, -0.7647977902465897, -0.65731757929027, -0.6712031005104421, -0.7632376919487882, -14, -0.6695358807736251, -0.6884240808656993, -14, -0.7225790930039161, -0.6602587430650603, -0.6606782252398667, -14, -0.6566383210528449, -0.6686273820037817, -0.6550017843193555] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0507  total reward: -1205.098207006836
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9722194829650976, -0.9958316849206661, -0.7943391897841254, -0.6484820333797363, -0.6010091352781031, -0.5927608581233407, -0.6635887188613774, -0.5659065852146385, -0.586251987635715, -0.6519074781333952, -14, -0.5823391718597316, -0.6007130115689774, -14, -0.6273397480279059, -0.5724113322790665, -0.5722851084731966, -14, -0.5704021181420212, -0.5878646134225691, -0.5686469091668014] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0508  total reward: -1206.2071729569782
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9388301532495144, -0.9573177363860235, -0.746413207710735, -0.6316781369629936, -0.5766855844650012, -0.5566621403409511, -0.6583250226061006, -0.5405479570911894, -0.5453665939932634, -0.5936330508651418, -14, -0.5543485830997085, -0.5641797481076003, -14, -14, -0.5433652230949599, -0.5548420809588868, -14, -0.5440405637379733, -0.5500412431769338, -0.5430593649276638] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0509  total reward: -1207.6254572577166
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3398973920821726, -1.6971020791944706, -1.1648495021820238, -0.9994543521357272, -0.9025938107765835, -0.8938771547777603, -0.9179549888245264, -0.8732155459508991, -0.9076979636302319, -1.3414876020006608, -14, -0.8861050643075888, -0.8926281674419683, -14, -0.9834421388281381, -0.8787155113246229, -0.9460064781173491, -14, -0.8778223912164789, -0.8761924986366602, -0.8777363436472223] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0510  total reward: -1209.2678677318884
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2945015186938418, -1.3176116738501324, -1.1017827926640105, -0.8974363202579579, -0.8160427708315908, -0.8007452767916041, -0.934129650292928, -0.7572840990244775, -0.7673187814119788, -0.8284129466346926, -14, -0.7846476481778747, -0.7995335875791576, -14, -14, -0.7699262118902069, -0.7914323385925944, -14, -0.7706652280179213, -0.7758771829828073, -0.7691949282208849] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0511  total reward: -1211.0756258978213
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.760053911319426, -1.8181352392068288, -1.4556286266503582, -1.204778016170879, -1.1090958804220516, -1.0880294968932749, -1.2251890742213403, -1.0477688673392693, -1.0852865016345354, -1.1876841502523687, -14, -1.0757682340670673, -1.1100332268523405, -14, -1.1750728662974268, -1.0571533146959917, -1.051757670146378, -14, -1.0536440136390308, -1.0923192503737946, -1.0504740669082815] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0512  total reward: -1213.54332121328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.063998139601265, -1.6408209227446335, -1.5069627821229064, -1.4969851641270437, -1.72529831072511, -1.4094401606297684, -1.4209540640361331, -1.5352774024836002, -14, -1.448991520226204, -1.475486641446449, -14, -14, -1.421444168251539, -1.454359330404413, -14, -1.422527703840607, -1.4409316962775753, -1.4199264481196254] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0513  total reward: -1215.6736968590076
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7398689239957508, -0.7301314365810873, -0.9474597929958501, -0.8533881361500488, -0.7147962694509397, -0.7235468888086113, -0.7241559546667763, -0.9089771568569471, -0.720403703060258, -0.7439383541587988, -14, -0.7508048599429815, -0.790141254903407, -14, -0.9712446953464343, -0.724432480743099, -0.7243933972605358, -14, -0.7262123928937103, -0.7628204271841162, -0.7209354850978625] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0514  total reward: -1217.1961125461007
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8074550062261497, -0.8045689151846603, -0.979628172963364, -0.8805321117289964, -0.8134987564259168, -0.8115613315326159, -0.8130845355415572, -1.0605653769767356, -0.8058403596436411, -0.8120020271971895, -14, -0.8458488140190005, -0.8902848968271477, -14, -1.1026677744677398, -0.8126210468192477, -0.8227021690428471, -14, -0.8121997273474366, -0.8561829997572574, -0.8076194176421257] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 0515  total reward: -1220.5204205770535
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
rewards [-14, -1.76282326401257, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 0516  total reward: -1223.8529141592937
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2369650898764633, -1.8025889419533432, -1.4863716896879406, -1.6356128215483916, -1.7691206457165678, -1.5748040478605123, -1.6029235958423138, -1.790894880437049, -14, -1.6033845182739352, -1.6567161453845545, -14, -1.6964283586143638, -1.5837444559854517, -1.5540502564682965, -14, -1.5748446015332096, -1.6287640714633949, -1.5696703182277054] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0517  total reward: -1227.1536513108308
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.156837500469717, -1.842326260063197, -1.912349451197879, -1.912066373198972, -14, -1.884550142955191, -1.8274245027747325, -1.886155045078236, -14, -1.8499721447214654, -1.8967887770434582, -14, -1.970546603581476, -1.8250813053988528, -1.7993955642040256, -14, -1.817275933301054, -1.865918865090352, -1.8143654618491298] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0518  total reward: -1230.0674134229014
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6634298658140287, -2.0911677108207556, -1.4420778201207385, -1.2564283631329438, -1.143041047202003, -1.1317168405567082, -1.1692908148479035, -1.1580455388646893, -1.1220309616616941, -14, -14, -1.1692031518060835, -1.255066188982742, -14, -1.2292555646924919, -1.1150315459510092, -1.0804186289852475, -14, -1.128515522477705, -14, -1.1143665478665163] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0519  total reward: -1232.2766902693375
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9375493566617663, -1.9705589483227903, -1.577807354357337, -1.3058914227173062, -1.1970528606756112, -1.167755952140201, -1.342151457673721, -1.1400106951257423, -1.1509228913873661, -1.265434713880604, -14, -1.1537914252679717, -1.1847758619560724, -14, -1.2359178621434863, -1.1380802689017284, -1.1294766557668943, -14, -1.1308920105431666, -1.1608770212706345, -1.1288582174508215] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0520  total reward: -1234.4581338878907
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7827704158716595, -1.8630768752111153, -1.463360000141704, -1.2134157544469863, -1.112409966770344, -1.0879969475457798, -1.2275718060900724, -1.055505851355847, -1.079435865108852, -1.1828343878880225, -14, -1.076129845682082, -1.1102671589321191, -14, -1.161810511327687, -1.0599059484774398, -1.0582321156468357, -14, -1.056262172637154, -1.0863855489459182, -1.0525854011025253] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0521  total reward: -1236.7289866789636
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.819890477430723, -1.42404210358532, -1.2943925581396847, -1.2903582652286918, -1.4569723838969202, -1.218345590258933, -1.2402849762349442, -1.345579840513005, -14, -1.2440783004145655, -1.279364177014789, -14, -1.2974707792019857, -1.226694693335218, -1.2143286096408181, -14, -1.2213492413328575, -1.2485227685305216, -1.218267389970309] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0522  total reward: -1239.2293939083243
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7210978678251607, -1.470420968793609, -1.341327352448325, -1.3143977879641475, -1.4521111098696131, -1.3242411208456668, -1.2992032572351115, -14, -14, -1.3395173162902625, -1.4159297829751791, -14, -1.414853505745224, -1.3004243761267231, -1.2801967903205982, -14, -1.2975062507996762, -14, -1.286078619719806] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0523  total reward: -1241.9592606065844
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1191563194553313, -1.658423043803993, -1.5340603883776878, -1.542000647771789, -1.7037420595087296, -1.4568378389914498, -1.4789417901018824, -1.6195959097234838, -14, -1.4819883755823473, -1.5258989949996047, -14, -1.5763542888040336, -1.460505685497457, -1.4524997100487012, -14, -1.4538146722952416, -1.4827216438831106, -1.4496699079396047] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0524  total reward: -1244.6856739939933
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7683587672392425, -1.4570304019416969, -1.3476563693780235, -1.3251632209214377, -1.4805779136217347, -1.2738753768890163, -1.3163291905164003, -1.4730399770786275, -14, -1.3096317707421459, -1.3477825729111184, -14, -1.419969071666581, -1.2853829306983786, -1.2815450472351044, -14, -1.2794821360372148, -1.3070804722678528, -1.2767434794693053] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0525  total reward: -1247.0082581112438
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7962320837321408, -1.8366873713451826, -1.4481591733787584, -1.2085710187605616, -1.1108835417633258, -1.081847938510171, -1.2558042478611107, -1.045153742014852, -1.0567125967680429, -1.1392784431373446, -14, -1.0723005632773874, -1.0926929854103673, -14, -14, -1.0495049227613908, -1.0781399038405244, -14, -1.0509826511488456, -1.0668856834930063, -1.0487087403614823] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0526  total reward: -1249.23661983922
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0166477686474646, -2.029061918972193, -1.718915163802751, -1.3514264659416244, -1.2523593915350153, -1.2565118872371033, -1.3960779083687145, -1.192231829506229, -1.2072578828461893, -1.309051849832883, -14, -1.2064687743798457, -1.2427050143284213, -14, -1.293489009152353, -1.191795925900354, -1.184978728352451, -14, -1.1871697933483427, -1.2241524754663509, -1.1832079859613966] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0527  total reward: -1251.6832462295754
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7801267421844096, -1.4263972368019107, -1.341252028659395, -1.3308292854274855, -1.5017470629938654, -1.265412534814005, -1.2896128739197368, -1.4135144316293375, -14, -1.290016207426962, -1.3255526239606845, -14, -1.3645372570594088, -1.2722921501724305, -1.2613080204884095, -14, -1.2663663835018695, -1.294562413966781, -1.2634184043939292] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0528  total reward: -1254.0558401927701
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8743335104878787, -2.0633285280992903, -1.4940364412071367, -1.2586294433320007, -1.1652904183339814, -1.142791019447041, -1.2802947664038726, -1.1404474288926842, -1.1217889637390512, -14, -14, -1.1531291324473198, -1.211268328088491, -14, -1.211636589640009, -1.1254644324471128, -1.1103819769006837, -14, -1.1197018865475958, -14, -1.1112859427063075] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0529  total reward: -1256.0791895710875
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6117575377708047, -1.6520166326122285, -1.240871657740265, -1.0638121455013345, -0.9706874768486586, -0.9308012182721759, -1.0909971175595539, -0.9006686097754109, -0.9428263763318776, -1.0523211931459167, -14, -0.9351887318338858, -0.9645659801005786, -14, -0.9843615720367423, -0.9185332760295304, -0.9138754820671577, -14, -0.9155114474350642, -0.9476009869057297, -0.912967401416703] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0530  total reward: -1257.9112749927901
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6824484761299918, -1.773297617133008, -1.29748445726114, -1.1168097335851725, -0.9959433468395045, -0.9458948902629362, -1.1530735151116749, -0.9379915337737539, -1.1318978546556362, -1.040831279997811, -14, -0.9607095412489469, -0.9938802360705634, -14, -14, -0.9286366983382903, -0.9311297996013289, -14, -0.9400175366913031, -1.0110630622664236, -0.9314168119273193] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0531  total reward: -1259.4446640960955
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0381559827110654, -1.0589285398314732, -0.8591064464779689, -0.7006274963176696, -0.6416620391945747, -0.6292947255513063, -0.7203860632431128, -0.6075415587556804, -0.6084563370165569, -0.6521221190937274, -0.6233917203337432, -0.6189680994227905, -0.6293810727500374, -14, -14, -0.6046659065971581, -0.6214095093431781, -0.612270105545662, -0.6066519311912593, -0.6116444619696616, -0.6047524049669627] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0532  total reward: -1260.9625405353713
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4297418281351753, -1.7258895449490486, -1.221031769279307, -1.0386886395612016, -0.9457107013258166, -0.9339085911981833, -0.9793240240041245, -0.9018568713068639, -0.9167753818144251, -1.274975334269387, -14, -0.9191009358220511, -0.9194695700853275, -14, -14, -0.9004310756011105, -1.0192724021144814, -14, -0.9129452205831898, -0.9189889210659141, -0.9132105326787974] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0533  total reward: -1262.5593544983267
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2080268925231719, -1.197802427638334, -0.9578088117571228, -0.7939348866611843, -0.7382360727507731, -0.7215810294604039, -0.8288450154599181, -0.6948570865184701, -0.6976673116307153, -0.745293251807597, -0.7171252649978713, -0.7146310236897405, -0.7271710709462231, -14, -14, -0.6961318665282477, -0.7221500670858487, -0.703336102663912, -0.698593024783301, -0.7039476002048114, -0.6963828873542962] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0534  total reward: -1264.2870095526937
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7754319403443843, -1.803223232955341, -1.4484953012452462, -1.1944966945753437, -1.0953466138784689, -1.0694848274432442, -1.2009127669527893, -1.0349147074834344, -1.0521990836905182, -1.1271239949558198, -1.0802483083107854, -1.0561324787558728, -1.0781016792377447, -14, -1.1233735669772071, -1.024535565450683, -1.0388669502957457, -1.0538020389908531, -1.0351595462349155, -1.0519225543396769, -1.0327979678485082] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0535  total reward: -1266.59349788329
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7587284028955186, -1.4664986226485475, -1.3565141225695059, -1.3230823647531684, -1.499378242100255, -1.282199886335671, -1.315757599981953, -1.478111037574039, -14, -1.3097058086318087, -1.347323164670187, -14, -1.4106080508601626, -1.2915420489735068, -1.2833532956526785, -14, -1.2854800751896582, -1.3058009431011324, -1.2819527651454086] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0536  total reward: -1269.42917282515
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.215190070943169, -1.7697818725318177, -1.6478377183286739, -1.6361914462624851, -1.8386264900183027, -1.5638838217572206, -1.5812121629638825, -1.7428916135125512, -14, -1.58639390708568, -1.6298197487177914, -14, -1.6791264226825138, -1.5661797944325642, -1.5524741477681967, -14, -1.5574654030416104, -1.5782527717707808, -1.5537221767149094] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0537  total reward: -1271.8359198329556
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9175468600451689, -0.8994279991052984, -1.0394028164687383, -0.9900903800964457, -0.8257270667910018, -0.853692630442518, -0.8523756364817695, -1.1053552008719985, -0.8501307843784149, -14, -14, -0.916650032008517, -1.0147022694244157, -14, -1.1353387313216174, -0.853110028090195, -0.827305501565188, -14, -0.8704948952596899, -14, -0.8542728600371831] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0538  total reward: -1274.399202652035
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3169208993059867, -1.939421707097789, -1.6725962849948657, -1.8011450499573294, -1.9264729855691525, -1.778396808909454, -1.751271245042227, -14, -14, -1.803776196337863, -1.9133750309911521, -14, -1.8740011657585065, -1.7673598281615557, -1.7388562665652327, -14, -1.7566405786390153, -14, -1.7375557522885146] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0539  total reward: -1277.7985748034453
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3830396149213717, -1.9472848078240814, -1.8024028737577602, -1.8019743807584352, -1.958880347553327, -1.7977668737343302, -1.7359472909431835, -14, -14, -1.7942461896617696, -1.9053792486671508, -14, -1.8970649160107833, -1.7461364959723813, -1.71726822028835, -14, -1.746037813994047, -14, -1.7267758664153703] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0540  total reward: -1281.4704412891738
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.824565727033244, -2.1937735323579224, -2.0683069102359917, -2.0974302960357827, -2.3002341124875283, -1.9766493925052417, -1.9897294633228118, -2.1768742890702653, -14, -1.9940748983927228, -2.04590210058677, -14, -2.1347193538884137, -1.96879290275428, -1.9623433489255435, -14, -1.9585541585145787, -2.0120993431109864, -1.9545982654401193] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0541  total reward: -1284.8875623238057
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0749752470180702, -1.6929872263128403, -1.545575738922943, -1.521399051092366, -1.7080165387862467, -1.4681827825884588, -1.4969165612353643, -1.6752995516395937, -14, -1.496180398158422, -1.5431085922048227, -14, -1.6074036658487079, -1.4737106909906963, -1.4753475103841656, -14, -1.4674152953889228, -1.4960329786948885, -1.4625227691918237] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0542  total reward: -1287.7974098519364
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.026347442469296, -1.6636202921200254, -1.5333623804864156, -1.5033409711033179, -1.7104343511234181, -1.4763342859491126, -1.4676182370880604, -1.6220497732276016, -14, -1.478563994303169, -1.5193091426411989, -14, -1.5829356072257759, -1.4600288521408429, -1.4565383844551882, -14, -1.450659649537046, -1.4732261974977696, -1.447324758938816] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0543  total reward: -1290.911600509333
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.500058288441259, -1.8825835633274264, -1.7698074604364467, -1.818744088812655, -2.0016622606892573, -1.6884405707922987, -1.6898111407028313, -1.7885055534064331, -14, -1.6981037450307956, -1.7465336672156342, -14, -1.7924045287510029, -1.6756080675503058, -1.6559926239773388, -14, -1.6717556311218624, -1.7139912222685507, -1.6668658984578173] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0544  total reward: -1293.7394645489785
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.911759789841189, -2.1767844256137896, -1.6076250588090921, -1.3312738834539324, -1.2234198570320565, -1.2130028781084192, -1.3228044467641669, -1.210765104474488, -1.1783744774866887, -14, -14, -1.2149366175452614, -1.281052406442023, -14, -1.2726137094326964, -1.1843876284954804, -1.164121834409884, -14, -1.1825472283569773, -14, -1.1718714156680121] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0545  total reward: -1296.1824616353492
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7793371143282408, -1.4576269914122175, -1.3524646001126006, -1.3318553315703543, -1.5025232017001464, -1.2817564875370897, -1.3152231732738564, -1.4175996424386539, -14, -1.3104164481138438, -1.3501931858183858, -14, -1.4235975929986298, -1.2867505309480776, -1.273918965477215, -14, -1.2819244535295886, -1.322883807309168, -1.2788752519608722] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0546  total reward: -1299.1886130061814
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4860624805090406, -1.9084505483916727, -1.8034827476496542, -1.8782692093347906, -1.9242032993862097, -1.8138820956439152, -1.7369990188290654, -14, -14, -1.7862246068455743, -1.8784137908818113, -14, -1.8949445400692186, -1.7488502137444792, -1.718671497613291, -14, -1.7487714365277927, -14, -1.7322324053550038] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0547  total reward: -1303.2916694872588
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.938196152995387, -2.4294028694656205, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0548  total reward: -1307.2184703220817
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.2973503482927273, -1.5734060379468844, -1.52595616456954, -1.9818696736373795, -1.5098247276614618, -1.522997657963153, -1.743123781413562, -14, -1.5329194887949888, -1.583749317284671, -14, -1.6041899247659783, -1.5126601814745013, -1.4731407377505308, -14, -1.500443876873555, -1.551410180686146, -1.4973979653572795] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0549  total reward: -1309.710046833176
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.1138459489359875, -2.0177159873309094, -1.7255620735665833, -1.3557753321349282, -1.2693471782028922, -1.2710142628969197, -1.4459664142843947, -1.2142992752128572, -1.209833935173867, -1.2674847731221777, -14, -1.2232238181123385, -1.2625771688381708, -14, -1.288771674926378, -1.2024858319574316, -1.1917883162805336, -14, -1.1975515738344897, -1.2425385189132623, -1.1942261628013975] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0550  total reward: -1312.055023132415
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8477768734255702, -2.1434330171466, -1.5441713947480997, -1.2727283513909025, -1.1942693248817517, -1.2006921132142754, -1.239900061319731, -1.1931641347803636, -1.1584685456465744, -14, -14, -1.2014229480948808, -1.2794234782579474, -14, -1.2496835680696399, -1.1567077967375639, -1.1268492732260216, -14, -1.1664649651704528, -14, -1.1531879829588485] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0551  total reward: -1313.8237834554525
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6657499179938134, -0.6576403878211309, -0.7722551023772383, -0.7477780664123588, -0.6319826844161546, -0.6404458794138683, -0.6404625956408082, -0.8102013661325205, -0.6426077150781776, -0.6431572021373062, -14, -0.6701146378499601, -0.700076369419737, -14, -0.9024674296426446, -0.6449611064557729, -0.6653637942552273, -14, -0.6452482558896763, -0.6705076638779709, -0.6419110498110923] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0552  total reward: -1315.4769942020325
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5368394161287742, -1.5184253212050227, -1.361846994935732, -1.179874257137453, -0.9680912629785338, -1.0356370048738712, -1.1507604903430175, -1.014740086782849, -1.049608632930844, -1.220776144531647, -14, -1.0454346815384576, -1.0838257300452725, -14, -1.1054264250414334, -1.030349485124093, -1.0175693004219701, -14, -1.025438073068505, -1.0553644795581334, -1.0212280621639855] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0553  total reward: -1317.8342400643028
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8025269383309093, -1.7720829183888955, -1.4300149683483907, -1.3875306660022757, -1.5076853105626185, -1.4075096415708102, -1.4954313134089736, -2.182752649584775, -14, -1.4038283803484939, -1.4194796722585605, -14, -1.4075096415708113, -1.3931521096260393, -1.4233541894350434, -14, -1.3903325681225396, -1.3936320957214823, -1.3891545992918028] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0554  total reward: -1320.0483508227971
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4958056066970749, -1.4441483500993197, -14, -0.9498883600406572, -0.867113239937762, -0.8030287600646732, -0.935037770019053, -0.8241798752846639, -0.8507222108229184, -0.9565384009171831, -14, -0.8442360028075682, -0.865945872298896, -14, -0.913161588641995, -0.8319202894201753, -0.8366584083486573, -14, -0.828522415151347, -0.8427335684717432, -0.8265800924921696] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0555  total reward: -1321.5871566749306
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.27969197115839, -1.2671916294041605, -1.0760377919078385, -0.8416853498492152, -0.780889100844677, -0.7831182506506278, -0.8787712854476523, -0.7444056781045446, -0.7472604382468, -0.8144620370401227, -14, -0.7500021353404001, -0.770227157022286, -14, -0.7959779010224025, -0.7412903379483639, -0.7335788963727485, -14, -0.7375470190718815, -0.752011131793445, -0.7357770920685341] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0556  total reward: -1322.958927383228
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0523530635662948, -1.1581165276699388, -0.8854622430231079, -0.7069097710859545, -0.6657598834060348, -0.6754762215898429, -0.7136633901009648, -0.6556545157695791, -0.6434155159244006, -14, -14, -0.6615065459846375, -0.6992887525345699, -14, -0.6938409299310819, -0.6439655918695595, -0.6335764285419372, -14, -0.6446364878946048, -14, -0.6381918119248138] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0557  total reward: -1324.323199859427
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2537030613042788, -1.2510336888445612, -1.0401265473400658, -0.8329769067638024, -0.7737097058116115, -0.7691890495946859, -0.8645755239153047, -0.7375625306093879, -0.7465407893812191, -0.8147597734504015, -14, -0.7455448468173501, -0.7659325351411086, -14, -0.8057881462213827, -0.7358295495576562, -0.7285356668274745, -14, -0.732351707794227, -0.7523982082999853, -0.7306960476569359] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0558  total reward: -1326.077770564409
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7284590439028502, -1.8918506425864554, -1.4080621039681376, -1.1414120291626764, -1.073058097892964, -1.0760831211907087, -1.1588362910500714, -1.0591133770362968, -1.0318222409676263, -14, -14, -1.059548346014751, -1.1117188874797848, -14, -1.1129586615387257, -1.0372830476606871, -1.0206962600846978, -14, -1.03458088811503, -14, -1.026035038154847] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0559  total reward: -1328.2418134425905
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9519825736184617, -1.9899600985721169, -1.6144320445836067, -1.302843493236185, -1.2085745762667544, -1.1985667803136424, -1.3363324795643687, -1.1432209984173192, -1.1745947016359295, -1.2887347228557966, -14, -1.1697811919502137, -1.2028280049527997, -14, -1.2608184362642982, -1.1513495276481025, -1.143129528617746, -14, -1.145856173150282, -1.1770815413555968, -1.1433466180964977] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0560  total reward: -1330.878034553991
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0805821072990667, -1.6491414685027626, -1.5614200172549337, -1.589099843522515, -1.6992149816070292, -1.5470091159948463, -1.5030803812321836, -14, -14, -1.5475145390780372, -1.634515286718958, -14, -1.6374380566171367, -1.5104513784328333, -1.4889254298361536, -14, -1.5077318568970157, -14, -1.4930915827829523] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0561  total reward: -1334.1174353363554
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3477593562053873, -2.0258155220587812, -1.862496628679967, -1.7815591057937599, -2.0935809967695116, -1.7494651111288262, -1.788587709874994, -2.0010488545237317, -14, -1.7877037406198122, -1.8373439340580313, -14, -1.8874180638137084, -1.763178235953008, -1.7546161968388927, -14, -1.7545424178456879, -1.7958595299957454, -1.7504753525281083] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0562  total reward: -1337.5635796116085
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3961414076107803, -1.9713307954387997, -1.8021503554672318, -1.7589714878304585, -2.062463267518427, -1.6904217576569591, -1.7038929487739867, -1.853611373233104, -14, -1.7315336517116235, -1.7646377460305582, -14, -14, -1.6982390583747482, -1.73520124533648, -14, -1.700486907356942, -1.7211371200196712, -1.6966791641244472] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0563  total reward: -1341.0450778548866
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4787261242050214, -2.04422481904292, -1.898958115101434, -1.8578748536772702, -2.1144360104032183, -1.8018307988350863, -1.8279192198815295, -2.030804381055454, -14, -1.8282010477080552, -1.8764217465267061, -14, -1.9544192823901847, -1.8048547134321893, -1.7912509078127514, -14, -1.7948340853659046, -1.8266361672623588, -1.791076485621106] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0564  total reward: -1344.5231894837302
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.344725886581968, -1.9656613981736593, -1.7840940152201292, -1.7334049966284262, -1.9686782270589458, -1.680399294134831, -1.7335975905536793, -1.9793050258328282, -14, -1.731098550147072, -1.7724272266809822, -14, -1.8438943533039218, -1.6996590765424833, -1.6969468968512278, -14, -1.6881973928334801, -1.7199243871603267, -1.6870351432224566] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0565  total reward: -1347.9127319497684
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3772385581220807, -1.922338288277051, -1.8040913723629421, -1.7938877543698595, -1.9989073375701514, -1.7040575949797487, -1.7259426549779215, -1.9211121995681268, -14, -1.743892181535229, -1.7704426071906758, -14, -14, -1.7086601016118683, -1.7773481239476872, -14, -1.7118689046931135, -1.7247848984809557, -1.709143171903347] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0566  total reward: -1350.4678527759013
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8672026616856534, -0.8581335846196357, -1.0643142057417208, -0.969560435059506, -0.8461236723991982, -0.8550138643746469, -0.8536775737010777, -1.1053192322156156, -0.8493137292295474, -0.8750965752534958, -14, -0.8869579305144409, -0.9267371551673899, -14, -1.17006344956321, -0.8548947864013088, -0.8632775479775151, -14, -0.8551245192684168, -0.8994256881808413, -0.8510632311531449] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0567  total reward: -1352.8601913378466
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1914995241083717, -1.7585783590910427, -1.4599779766317909, -1.6188887606527935, -1.748982665941116, -1.558780426845853, -1.5722165514307764, -1.7549731566726015, -14, -1.5785783928885138, -1.6298707203341396, -14, -1.6602473287321404, -1.559194180202628, -1.5334652160586764, -14, -1.551160874022043, -1.6003529919920039, -1.5462148895460515] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0568  total reward: -1355.7073174991626
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0058574979152577, -1.6153289402868976, -1.4701261895100677, -1.4494641766622365, -1.6339841763474512, -1.376833923784487, -1.4243467703680337, -1.5853668441023738, -14, -1.414878470671864, -1.4557828798615593, -14, -1.49499331055655, -1.3961170006785357, -1.385911660198784, -14, -1.391444670330619, -1.4215631121710972, -1.3871481846842992] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0569  total reward: -1358.4045604007517
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8167530747764458, -1.5482763352493196, -1.400021611521375, -1.348954088697385, -1.5875884142493684, -1.3109176325835246, -1.3239092828954226, -1.4668198622309037, -14, -1.3469183767063764, -1.3712824071926932, -14, -14, -1.3204954001201714, -1.358800564522641, -14, -1.3231497157475296, -1.3293549053723381, -1.3204089778046875] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0570  total reward: -1361.8401889764627
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0380984046742734, -2.568523734258602, -2.288266032992034, -2.170396568996464, -14, -2.1067760051523643, -2.2335195820577365, -2.3043332467080586, -14, -2.1743390161730587, -2.2534781428459985, -14, -2.1067760051523643, -2.1125645623337874, -2.1058466581103765, -14, -2.1334090654443143, -2.3010159353363044, -2.1247109431273623] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0571  total reward: -1365.6909516864773
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4098281619373902, -1.9818231887104372, -1.8325198781730467, -1.8125000086365164, -2.032266443020698, -1.7903517744394595, -1.760097499985, -14, -14, -1.8041865912765749, -1.890013053671359, -14, -1.8963916942043215, -1.767696320871661, -1.7482427990380172, -14, -1.7579326159436945, -14, -1.7449160519042395] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0572  total reward: -1368.7637461690988
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7821164532066878, -1.4940283722047514, -1.3766919714101304, -1.3691871532295077, -1.4513717245151305, -1.3655042844194591, -1.342274585903491, -14, -14, -1.3837237822662471, -1.4707191266893942, -14, -1.4607917538386388, -1.3378372964709322, -1.3101818840757409, -14, -1.3421389357013993, -14, -1.3278784307171483] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0573  total reward: -1371.9373339604203
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.827472994175525, -2.018214298900181, -1.9744722142032989, -2.1423052028648617, -14, -1.9124831036561813, -1.8760019671343298, -1.9628086894007246, -14, -1.8920942981694124, -1.9372762252092197, -14, -1.9839185360524618, -1.8741520192975618, -1.851267646436098, -14, -1.8674905480682817, -1.911920274116109, -1.8634059072458573] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0574  total reward: -1375.0618249172926
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7045023937435324, -1.4503913557372161, -1.3353965755774935, -1.3042785479836367, -1.4799292315497063, -1.3015388867484083, -1.2910025281360287, -14, -14, -1.3248883610127504, -1.4052873075043146, -14, -1.3999977102954984, -1.2900993508090004, -1.2744136846855154, -14, -1.2863883303396277, -14, -1.2732233104361244] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0575  total reward: -1377.7467611969807
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9227814512734855, -1.625368051874624, -1.4878535866946323, -1.4475257984829453, -1.678367668081233, -1.4162173273359642, -1.4436909683100825, -14, -14, -1.4585867748013583, -1.5326935013732639, -14, -1.526202076313204, -1.4304178377687051, -1.4196078605600806, -14, -1.4240450945675, -14, -1.4117129692521748] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0576  total reward: -1380.090798915102
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5331153922659027, -1.7075551487599738, -1.2959240426908722, -1.0556081155186061, -0.9752629719913541, -0.9730740404032308, -1.0642506293183736, -0.9561587260869336, -0.9407089872081956, -14, -14, -0.9681595328446931, -1.0215790421097273, -14, -1.013521999965251, -0.942899590763147, -0.929928288564681, -14, -0.9406864353976203, -14, -0.9323247488690516] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0577  total reward: -1382.2301018177589
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6892585145056358, -1.5020432601774525, -1.2966153137397245, -1.2170666189874737, -1.5030234783911196, -1.2040979788357868, -1.2763424608544398, -1.3833205936882547, -14, -1.2380906182101576, -1.2889140199618687, -14, -1.2040979788357873, -1.2093321836813478, -1.1984114495009248, -14, -1.2169411750985406, -1.2789899294750844, -1.2093746140922115] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0578  total reward: -1384.2197844720254
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2974938924314146, -1.4214776367258217, -1.10474712874257, -0.8898603730913572, -0.8277073783320456, -0.8317759918162829, -0.9054575101819786, -0.8226295382359736, -0.7962735464214936, -14, -14, -0.8194426661811492, -0.8656875417470082, -14, -0.8713135466545929, -0.801371710638135, -0.7905275578901595, -14, -0.7992599774158325, -14, -0.7912712047655907] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0579  total reward: -1385.3428166477038
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3439528518880888, -0.34025633239571434, -0.4272791715219127, -0.4010752504277028, -0.3280146518101972, -0.3317048712908521, -0.3332318958774118, -0.41691430286197945, -0.3324824146634823, -0.3372311409562891, -14, -0.3468257677750333, -0.3625886762592273, -14, -0.45069136600348175, -0.33419357997449106, -0.33701818998318184, -14, -0.33412677177927697, -0.350830353334728, -0.33250461778831814] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0580  total reward: -1386.371104107587
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0579084533707115, -1.0177419879190817, -0.9462551482926733, -0.8066437430899662, -0.6610856720345533, -0.7134748468758952, -0.7953072969685794, -0.707088267441184, -0.7133620695209638, -0.802167073258308, -14, -0.7167719007525931, -0.7402470976764957, -14, -0.759174141330728, -0.7066417410596993, -0.6945453362717362, -14, -0.7020572668186374, -0.7280243246490748, -0.7002728080728061] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0581  total reward: -1387.4685977125357
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4429961609228371, -0.43945960843085663, -0.5574253231483018, -0.4966255039687635, -0.4345746627481878, -0.440821231660359, -0.4385475548709185, -0.5649874146873923, -0.4355297171404171, -0.4542462505230187, -14, -0.4536242625357675, -0.4763285772853777, -14, -0.5944566137710281, -0.43805496745746736, -0.4421649508348976, -14, -0.4393679963508307, -0.4680172049022405, -0.4364079329142958] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0582  total reward: -1388.9104993737203
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.504935256085608, -1.436511778594593, -1.4275911204768466, -1.1581751987440914, -0.9507712810102326, -1.0455308711127942, -1.144319517417764, -1.0284568667450469, -1.0204273413672316, -1.1157853058910159, -14, -1.0287118967965918, -1.0611459566903727, -14, -1.0881978504433174, -1.016399636030673, -0.995052240771653, -14, -1.009960589966398, -1.043730569878794, -1.0073269984363078] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0583  total reward: -1391.111191454877
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.811579188244933, -1.406567351878779, -1.324210403696942, -1.3413580994099357, -1.4858388839822552, -1.2669228770278673, -1.2713973608660605, -1.3637618755255059, -14, -1.2758389650352926, -1.311622426538477, -14, -1.3655814107615334, -1.2586944996931073, -1.2470408380306324, -14, -1.2529016752728621, -1.2900077748275136, -1.2499208001465063] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0584  total reward: -1393.7949715045634
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9842174392057133, -1.61236136308093, -1.4951692937965646, -1.5031588095586828, -1.595521805129288, -1.4760984332081821, -1.449435448193936, -14, -14, -1.4911559286037108, -1.5799231540448602, -14, -1.5660595567352091, -1.4492079171949512, -1.4225921702046331, -14, -1.4519793725480554, -14, -1.4367392116556386] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0585  total reward: -1396.7151230673496
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.097789696324138, -1.7160713591112033, -1.5840415722721002, -1.558776969877935, -1.7573868710012186, -1.521780792355662, -1.5237039776282066, -1.6796774412666313, -14, -1.528727921138803, -1.569302146381961, -14, -1.6498117827225058, -1.5102267707301356, -1.4990862198280264, -14, -1.5007803382200229, -1.5240589251289522, -1.4975593925817638] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0586  total reward: -1399.6865154031127
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9828952726175328, -1.694985878889177, -1.5545016185613363, -1.5055058755745416, -1.697301585649293, -1.46565695553602, -1.5203970553934545, -1.7503685572800125, -14, -1.510755892349286, -1.5520784492909852, -14, -1.6274440719600678, -1.4850384616376109, -1.4980857141556443, -14, -1.476641895586175, -1.5109734900182952, -1.4738329431813417] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0587  total reward: -1403.0335215838652
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6412409186203276, -2.1311952286851708, -1.9931718424526612, -1.976783714292158, -2.268100903463563, -1.852237478795361, -1.877908348857829, -2.0329472517238605, -14, -1.9156749911459636, -1.9488077944586364, -14, -14, -1.8844836791547575, -1.95218261626518, -14, -1.8846213361564503, -1.9100606663754105, -1.8813492252164437] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0588  total reward: -1406.5835008625534
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4176807648082765, -1.9570463884968863, -1.7937305240512997, -1.773582313834851, -1.9808660108454106, -1.7118142108705554, -1.7336096053270125, -1.9556167915857205, -14, -1.7303704983719443, -1.7762694443740041, -14, -1.867879223459529, -1.7118903917086767, -1.7016804318225773, -14, -1.7020945587753737, -1.7232563425370269, -1.6977417998927051] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0589  total reward: -1409.9619484792695
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3535152612082024, -1.9373505681798715, -1.7822832739735448, -1.7423894445995913, -1.9875980723059883, -1.6776174285287428, -1.7217301787010366, -1.9202871312982746, -14, -1.7169336171156813, -1.7677924511936112, -14, -1.8248353640351187, -1.6932928350382737, -1.6846249215067715, -14, -1.685638405072433, -1.7235398336584604, -1.680705816823424] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0590  total reward: -1413.0829650906967
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0045551206096626, -1.65940174830544, -1.5283612022540487, -1.4935212353156917, -1.7146583939958449, -1.4453862719889752, -1.461905772412931, -1.6124929931429415, -14, -1.4739526734274926, -1.4991051614548152, -14, -14, -1.442723284584, -1.4873984645347875, -14, -1.4462584638098037, -1.4618904084851054, -1.443399182898644] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0591  total reward: -1415.9111016958702
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9749341809707777, -1.6073747381411527, -1.4721913929454205, -1.4430635952081896, -1.6655635346981612, -1.3830640301001458, -1.384842305326048, -1.4743781406914218, -1.4286743805028994, -1.4115820018745922, -1.4309812513253137, -14, -14, -1.3849657566949372, -1.416262658426425, -1.4014602201372668, -1.3885840008221573, -1.403265970387743, -1.385413320589429] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0592  total reward: -1418.5148694681766
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6898715753024411, -1.3908917829952734, -1.2938761406816872, -1.2676777539494077, -1.414408857738819, -1.2175995867958826, -1.2472743248311229, -1.3336980438789694, -1.2815587917897373, -1.2461064933945138, -1.273726427135498, -14, -1.3317463411466592, -1.2114645315255952, -1.2307506672427924, -1.2481706315156478, -1.2243002619376753, -1.2523415615043003, -1.2207037422059852] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0593  total reward: -1421.2748732574341
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8430139493960809, -1.5584379289796815, -1.6247654020910518, -1.6573063549529488, -14, -1.609725907437664, -1.5609511519174701, -1.5821683003421847, -14, -1.5806153990567273, -1.6280192622603415, -14, -1.6893001168609731, -1.5570445462989715, -1.5333763299067373, -14, -1.5526425870698601, -1.6127116798533103, -1.5485392577319619] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0594  total reward: -1424.4934870822804
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2514436058576313, -2.072991085927066, -1.7845463332506675, -1.6862009869452244, -2.0734660584364653, -1.6916065548336563, -1.7871251265960324, -14, -14, -1.7463309215138252, -1.8453347376128961, -14, -1.6916065548336567, -1.6985139595380505, -1.6963963881054684, -14, -1.7021250312298306, -14, -1.6852374949394981] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0595  total reward: -1427.894053169064
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3948550114656952, -1.9026919277351233, -1.800493119927398, -1.8195207998002096, -1.976673593892866, -1.7474319118337736, -1.7331847804858702, -14, -14, -1.7700041268539983, -1.8573438928442019, -14, -1.8504525233415747, -1.7359158646323551, -1.7151322252632595, -14, -1.7300150060969237, -14, -1.7153285918441321] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0596  total reward: -1431.0483050649716
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1011434471864057, -1.6803593288629577, -1.5176783236741032, -1.5085568053145306, -1.6675338723901907, -1.4436361797726642, -1.4723784122355659, -1.6357089284369968, -14, -1.4708590808043365, -1.5141892988871501, -14, -1.5768228029396456, -1.4500118839241465, -1.451694649972756, -14, -1.4434189949651486, -1.4746615520829636, -1.439119670644433] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0597  total reward: -1433.6652485816833
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.995141244458469, -2.043646487077497, -1.621717317957514, -1.3621840796627118, -1.2470036154911113, -1.2115525788360992, -1.3931587414653275, -1.1802114919469981, -1.210796982624039, -1.3258528676504304, -14, -1.208955242689738, -1.2483342263547708, -14, -1.3081990787310374, -1.1858485352624148, -1.1785101976921084, -14, -1.1810122353128776, -1.2181536970088214, -1.1778238460672643] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0598  total reward: -1436.1914886664674
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8933317550605626, -1.7169339938817496, -1.4416850066500602, -1.3518725021929392, -1.6620841748775237, -1.3435659304122485, -1.4198140216100155, -1.5413175972482651, -14, -1.3861047551402685, -1.44296652499367, -14, -1.3435659304122494, -1.35061905256597, -1.3381897513069358, -14, -1.355726113350074, -1.4203288524784081, -1.348416238716819] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0599  total reward: -1439.771889156334
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.441400688357705, -2.2188862124306183, -14, -2.2633182766913356, -2.140986848777639, -2.371239739282586, -2.2402758419904183, -14, -14, -2.2933842962316002, -2.366520651375859, -14, -2.406379098382996, -2.1842245384347208, -2.1103594778325308, -14, -2.253142204295767, -14, -2.242210738559604] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0600  total reward: -1442.7454678086635
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4563377904168413, -1.527858491456721, -1.2096252558413156, -0.9999586062252522, -0.912646653058718, -0.892859174380315, -1.009492224558704, -0.8597970766183816, -0.8873836760494096, -0.9873552883362423, -14, -0.8851483194882067, -0.9133356290395838, -14, -0.9444964518457211, -0.8697500042935421, -0.8723822800713533, -14, -0.8657796660132853, -0.8921287664424536, -0.8632191744970408] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0601  total reward: -1445.2368180267363
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.483572433942489, -1.9610718928561413, -1.7564900000489265, -1.7137189874211203, -2.1223026638115936, -1.6503257242504452, -1.8443609210046157, -1.726275461608036, -14, -1.675112109453797, -1.732699461046585, -14, -14, -1.6178630470303945, -1.6408264492238671, -14, -1.6447052056008287, -1.7782004887810479, -1.6315531414543396] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0602  total reward: -1447.740342448299
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.02521383320269, -1.4122783998658324, -1.0550962855993156, -0.9036985053951613, -0.935363774919516, -0.9315572285716517, -1.1284669106244483, -0.8688117540711446, -0.8799295227541322, -0.889296086043762, -0.9172750512417533, -0.9005225684516165, -0.9164403043447447, -14, -14, -0.8830641108748535, -0.8946698890422926, -0.9019339135051881, -0.888456473897963, -0.9011867125807035, -0.8856613745324032] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0603  total reward: -1449.3899912692161
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3886020971101847, -1.342723767981587, -1.1394982191663692, -0.8938796687774891, -0.8311527223191164, -0.829321086298127, -0.9240255762052776, -0.7879079411241862, -0.7894350749301028, -0.8369079980553855, -0.8107679687669697, -0.7944710193711866, -0.8096825669324015, -14, -0.829420950629907, -0.7750521855307282, -0.7823991330365982, -0.7946823136939148, -0.7826805904532255, -0.793591696213637, -0.7808370668459582] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0604  total reward: -1450.9150705871607
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.109250909629563, -1.4650674865828106, -0.9706215968384784, -0.8629816551046927, -0.7667186667803617, -0.7552579919732627, -0.7761893241462746, -0.7476315905721219, -0.775815892912236, -1.1903801545956523, -14, -0.7584661016654718, -0.762935761954036, -14, -0.848376617135847, -0.7499859788585171, -0.8090039025130332, -14, -0.7498523418818588, -0.7511294455275791, -0.7500271324139176] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0605  total reward: -1452.3730005009525
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.274865285769127, -1.235385494734119, -0.9946262897110127, -0.7979935858465423, -0.7537028261276348, -0.7489216587222146, -0.8559285173154175, -0.7106823910219191, -0.7172342905752482, -0.7778100644963646, -14, -0.7251797131198495, -0.7392573706432137, -14, -14, -0.7108427175464578, -0.7270396466805801, -14, -0.7121038854765062, -0.7216934470838589, -0.7102983232196077] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0606  total reward: -1454.012775459882
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5860204370653868, -1.6188524620839233, -1.2450256622474642, -1.0734605848438887, -0.9844906627901322, -0.9475145486872056, -1.1155971914624807, -0.9154183661541637, -0.9288494184114322, -1.0155872223398994, -14, -0.9468254278931372, -0.962873332646732, -14, -14, -0.9297493809155083, -0.958516074895159, -14, -0.9310835053825242, -0.9371399130422484, -0.9294766357098945] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0607  total reward: -1455.9451095969061
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.714599079412431, -1.798728491243999, -1.4189489005786757, -1.185760522149214, -1.0762948539392005, -1.0466409127325504, -1.1965301854986332, -1.0157790402121334, -1.0448984032358906, -1.139592125768047, -14, -1.041791877744258, -1.0756438233773955, -14, -1.1187596582899808, -1.023368603998272, -1.0200009151115603, -14, -1.0201286963124359, -1.0553849608524377, -1.0169157708699677] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0608  total reward: -1458.6552251163816
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.525536712966322, -1.934511166671163, -1.8053136494321953, -1.8263350991578287, -2.104499148142509, -1.6771100959914327, -1.6882478454492056, -1.794023245570752, -14, -1.7201732303976254, -1.7510261537618934, -14, -14, -1.6979392103226507, -1.7141857291995486, -14, -1.697856421014252, -1.7205933741379884, -1.6943364792635287] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0609  total reward: -1461.8857362019403
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.205512378190797, -1.7745705225968813, -1.6436930723306435, -1.6298040671345875, -1.8231426081351711, -1.5669902082930933, -1.583419337098968, -1.7509995199170836, -14, -1.5927435138462618, -1.641144236548486, -14, -1.6990196483467144, -1.565425943445545, -1.5672807696110584, -14, -1.5574132150906346, -1.5866106758935012, -1.5534009895671432] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0610  total reward: -1465.061084589242
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.28972766364794, -1.8489631708985346, -1.7152675981971284, -1.6991175400387595, -1.895086026726365, -1.6215491015247219, -1.6642724185966877, -1.8478912259691709, -14, -1.6600918213578244, -1.7048214764406555, -14, -1.7802841092971444, -1.632900695623744, -1.6277764211798882, -14, -1.6248753847376567, -1.6665278695271657, -1.6219473977346555] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0611  total reward: -1468.3823133705973
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3549375726770183, -1.93096726159624, -1.804946357598667, -1.7687730258685304, -2.042732763889689, -1.70373337399455, -1.7192277519609478, -1.8990307596002325, -14, -1.7365065104158701, -1.7621630460353903, -14, -14, -1.7003901592749755, -1.7416237012882132, -14, -1.701586764266763, -1.7217309098877844, -1.699679679830558] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0612  total reward: -1471.750085999591
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.395341498082105, -1.8892632663143063, -1.7720905522291612, -1.773850917012029, -2.0491087734570677, -1.629723825801039, -1.6640662145087657, -1.7539772278349035, -14, -1.698946936339879, -1.7287483518813012, -14, -14, -1.671689336338681, -1.7031643189627548, -14, -1.6703372526274625, -1.680392464483213, -1.6680929491631178] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0613  total reward: -1475.4833186444264
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5108381492066294, -2.1283002442336874, -14, -14, -14, -2.214222484768591, -2.1154253321239467, -2.1413037317428327, -14, -2.1450861463681514, -2.213505221925594, -14, -2.305503528319386, -2.114634409179427, -2.0841781339626735, -14, -2.110837019964756, -2.1811574130108333, -2.103508819034361] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0614  total reward: -1478.8988476525096
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8376447149770654, -1.5074548278513566, -1.396137178585351, -1.3856678934443099, -1.5434036095317305, -1.3782187603954104, -1.3395791961636359, -14, -14, -1.3798751547489976, -1.4513237467517353, -14, -1.4546486136187198, -1.3490061445169443, -1.3310716546973498, -14, -1.3423867471987605, -14, -1.331350874120646] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0615  total reward: -1481.922386881304
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.599579767802039, -1.8851155665175126, -1.7932301611058676, -1.9014940366203654, -2.0273693969996307, -1.7178486350679238, -1.714173693609139, -1.8027293247643632, -14, -1.727365880696784, -1.7753674466216782, -14, -1.8201569789798684, -1.703404894548218, -1.6809551592686796, -14, -1.6963932939754167, -1.7380374288000457, -1.692467574096951] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0616  total reward: -1485.1292517545492
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.402083314758596, -1.7025013595605984, -1.608188464733723, -1.7392949550906485, -1.8443357640228972, -1.5766410724790074, -1.5310721192471566, -14, -14, -1.5670832431717576, -1.6257185633334441, -14, -1.6401177471036272, -1.5474056258545275, -1.5382079628314085, -14, -1.5346388291815485, -14, -1.5259097139763833] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0617  total reward: -1487.910545150252
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7267469354853142, -1.407580921441278, -1.3133824754997916, -1.3114752357168609, -1.4258158145059754, -1.2924678872826485, -1.263590160377052, -14, -14, -1.300820383724841, -1.3753562368088506, -14, -1.3608794622229827, -1.2697621082777244, -1.2487705917047016, -14, -1.2682511317110619, -14, -1.2553836817263606] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0618  total reward: -1490.0397910357285
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8899717435689325, -0.8810694490547007, -1.140334133570659, -0.9991350985577988, -0.8793034209325636, -0.893602514719216, -0.8880334698799932, -1.1233702187846906, -0.8796922946345542, -0.932227892152842, -14, -0.9209698970257226, -0.9724807180700146, -14, -1.1949729724560076, -0.8819175972079345, -0.8825075604494863, -14, -0.8868451359553934, -0.9542550009268367, -0.8804752937720818] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0619  total reward: -1492.4991365817978
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.21866854062025, -1.8240027031138535, -1.4891780223593807, -1.629782888158119, -1.8013187014109975, -1.5897138956596173, -1.6069346358686771, -1.7689233485691171, -14, -1.6200730395138263, -1.6820602289904947, -14, -1.690146589996785, -1.592398264537513, -1.5652309204153199, -14, -1.5862833640693976, -1.641465884013713, -1.5800421251366108] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0620  total reward: -1495.168263653405
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9719314008355693, -2.1105712290181935, -1.6442741653427184, -1.3391318238558818, -1.240339842412709, -1.2311642544271548, -1.3370670925113002, -1.1865315871269921, -1.2091089364142227, -1.3949916970555472, -14, -1.2033136182550856, -1.2281928411431504, -14, -1.3106365791217072, -1.1885651552432794, -1.1992480082238346, -14, -1.181152371784423, -1.201027766943425, -1.179949049247661] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0621  total reward: -1497.5577680677418
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.720088973528849, -1.3986969707230026, -1.281638897011696, -1.2596313696880763, -1.421854790162259, -1.2112479938195213, -1.2349527537305125, -1.3996790003686392, -14, -1.232511434778746, -1.2629056505296916, -14, -1.3081026884476696, -1.2188716753201818, -1.2142476568362444, -14, -1.2119918338236957, -1.2319905869972778, -1.209555365089358] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0622  total reward: -1500.0102830801284
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6858497741928629, -1.4198851172397966, -1.3198734773176513, -1.2775151801115259, -1.4718421537228652, -1.2371529339638614, -1.2748387434153685, -1.418530258777467, -14, -1.2713378833639422, -1.3072637852242521, -14, -1.3451730025625788, -1.251738224752752, -1.242216639465353, -14, -1.2458188969459612, -1.2707612357060205, -1.2429596472972317] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0623  total reward: -1502.3817270859738
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8779369698842523, -1.9996831364186771, -1.5943351041952274, -1.3384898824080604, -1.20057252610281, -1.1644288040175057, -1.3574661553119323, -1.1341178771659852, -1.1472026700298736, -1.2540048630426734, -14, -1.160388984634257, -1.1823732055062603, -14, -14, -1.1344183099079141, -1.1680774738671584, -14, -1.1367890430720464, -1.1524989006477189, -1.1342910718815] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0624  total reward: -1504.2523238014255
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2683795841970515, -1.3116772338412286, -1.0295309132269115, -0.8538682233962506, -0.7806597511479875, -0.760590023979731, -0.8697912186808961, -0.7291870289412175, -0.7602557503956858, -0.8486950513849373, -14, -0.7539597122821055, -0.7756687253805565, -14, -0.803153201214495, -0.7409198344532801, -0.7358743490280192, -14, -0.7380844275769974, -0.7596712020610253, -0.7364788382856045] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0625  total reward: -1505.5467950229845
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9691688199759313, -0.9870097328323146, -0.7757744743100328, -0.646240302593084, -0.5980714524331144, -0.5841860036449998, -0.6723833137498721, -0.5612087836558498, -0.5679642990209446, -0.6228135745771702, -14, -0.5755078421095883, -0.5859801641612181, -14, -14, -0.5654259252476009, -0.581762258998294, -14, -0.566715198828492, -0.5709306573528665, -0.565284192618115] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0626  total reward: -1506.7540421187955
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4448532512175312, -1.0264874249158087, -0.7941425887524737, -0.6511094928885014, -0.6791562400501333, -0.7047295291099849, -0.7952248718836712, -0.6709013483629912, -0.6493159034583523, -0.6629533886388568, -14, -0.6580406016631563, -0.6780982140844407, -14, -0.6928958351706793, -0.6495251666727497, -0.6416139857436499, -14, -0.648287259668584, -0.666305900499477, -0.6460383121550453] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0627  total reward: -1507.8322149374449
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7037441688402151, -0.78328781125077, -0.611520482187689, -0.4894090003619318, -0.45532527547135304, -0.4606228907673236, -0.4918758427752988, -0.45464207822961317, -0.43884510760625556, -14, -14, -0.45165607762199844, -0.475929657730753, -14, -0.47967474947140093, -0.4412583433152578, -0.4345852588639864, -14, -0.44066704105356996, -14, -0.4365588329056202] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0628  total reward: -1508.6773626249183
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7231131674792954, -0.7069797362539465, -0.5773898167104712, -0.4789184770541164, -0.437852220420206, -0.42411003173952366, -0.5044809739653476, -0.41567141129132845, -0.41679399011187795, -0.4356130850106433, -14, -0.42020788964488387, -0.434907150684116, -14, -0.44275478750964076, -0.4133435425685771, -0.40721505658643276, -14, -0.4120582580521682, -0.4272972588111836, -0.4105624286096437] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0629  total reward: -1509.5570552818363
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8063191171016464, -0.8410858745222132, -0.6930631210162205, -0.5247072766197004, -0.49639508644291913, -0.5155108152504391, -0.5510371359912064, -0.4859830711432069, -0.47473784440552014, -14, -14, -0.48861565240703614, -0.5085818257277172, -14, -0.5074697482335966, -0.47842439423781735, -0.4734127531143384, -14, -0.47498228647542623, -14, -0.472477600331461] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0630  total reward: -1510.5901224533682
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8810265222601286, -1.0581044334821648, -0.7522258632469202, -0.6395033824852492, -0.5810999816067554, -0.5736483729560945, -0.6133075981632432, -0.573324482502493, -0.5676485917773034, -14, -14, -0.5831826225360482, -0.6177360964477745, -14, -0.6140995264488731, -0.5649216561882496, -0.5546654734443128, -14, -0.5661467494482331, -14, -0.5605895712004219] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0631  total reward: -1511.8921182322115
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.300179257565406, -1.3586775241617446, -1.0212231943379517, -0.8615167837221863, -0.7912271521359291, -0.7667573191932496, -0.8732815694905743, -0.7451060511507996, -0.7670009119262049, -0.8673621457267352, -14, -0.7639590592128205, -0.7827542639119732, -14, -0.8151680472669233, -0.7529646667544305, -0.747892627436086, -14, -0.7484230477586716, -0.7599664114482232, -0.7473303053991571] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0632  total reward: -1513.6821417417846
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8258984624589703, -1.740354613450399, -1.4963353481912602, -1.1986312936581627, -1.1119223856749174, -1.0999327294991508, -1.2996761994273132, -1.0308075156688967, -1.0417187564880668, -1.0939641367868502, -14, -1.0654474464110146, -1.08719231324032, -14, -14, -1.047050454650484, -1.055670990456209, -14, -1.0471978891999956, -1.063642771560784, -1.0449174584219125] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0633  total reward: -1515.6535378883716
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5235691148696513, -1.6722097469583344, -1.3623580194094784, -1.1112078123707267, -0.9918497458608725, -0.9758256032681506, -1.0908856781401723, -0.9418843481258441, -0.964456002060091, -1.0813318298826158, -14, -0.9627508512128891, -0.9865057979758415, -14, -1.0343843946979534, -0.9474745090297843, -0.9452727302349879, -14, -0.9417439771803949, -0.962873719490064, -0.940588630918203] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0634  total reward: -1517.6593083040507
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8007588283727198, -1.8878306458683802, -1.4468237647044364, -1.2252261024203548, -1.1246451318792599, -1.092300394294282, -1.2371087875138427, -1.0650981185788513, -1.0975436137748478, -1.2324336896119303, -14, -1.0898782387954793, -1.1200663930479986, -14, -1.1885425501608797, -1.0728119501136266, -1.068406346686017, -14, -1.0674056848706248, -1.0925930864950846, -1.0651817847610534] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0635  total reward: -1519.7611178145166
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7076267157044502, -1.7889612740409921, -1.4626306878207378, -1.2049710671191327, -1.0951993215644205, -1.0743257509385717, -1.2304996245600903, -1.016151023175932, -1.0346456642273738, -1.129315653837977, -14, -1.0566114088010337, -1.0719444169787913, -14, -14, -1.0364129763980316, -1.0719461189116568, -14, -1.0376532348327985, -1.0404464276919518, -1.0367113918868887] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0636  total reward: -1522.3467515692805
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.132366000079518, -1.7876671214974897, -1.6204826286586975, -1.6120413707082817, -1.6585878651126875, -1.5748924960284698, -1.6062216021663458, -2.3472997592934934, -14, -1.5819081742613934, -1.5886449448456732, -14, -1.7380535475034706, -1.571438644402211, -1.6579440193406443, -14, -1.5688980375598056, -1.5674062303856557, -1.5694827315880429] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0637  total reward: -1524.9619417963872
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7914896978846848, -1.7603255640691713, -1.5221914617437806, -1.2313140811342382, -1.1164647404694028, -1.0942886854911318, -1.3876995529402274, -1.0457378139864026, -1.0913489630736033, -14, -14, -1.0620617039525437, -1.074192133661225, -14, -1.1770680609524455, -1.0531507508715083, -14, -14, -1.0485552132687792, -1.0208529212840107, -1.0477839967211708] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0638  total reward: -1526.9973588685787
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7541118162817129, -1.752551299795516, -1.470669885556629, -1.1576537427486842, -1.0752019052787567, -1.076727396112753, -1.2022232368960395, -1.0356707943941705, -1.026990427926929, -1.1268478018311816, -14, -1.0344039813752064, -1.0608185070116876, -14, -1.1019195390478416, -1.0231662816087121, -1.016684915793296, -14, -1.0166449506125699, -1.0315027901547267, -1.01456415090729] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0639  total reward: -1528.9038327361304
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5746826910365426, -1.5911705563669127, -1.211131253156494, -1.0260141458133178, -0.9468987284264984, -0.9144127154830193, -1.0600887963026637, -0.8862965145186208, -0.9183405422490778, -1.0108504605802484, -14, -0.9111131873679418, -0.9401605551293353, -14, -0.9742280120621972, -0.8972979196658943, -0.8896831868413363, -14, -0.8950403907280727, -0.9219218625110025, -0.8919097166444817] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0640  total reward: -1530.5321038053123
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2488604239990053, -1.2830041549513214, -1.079277413306074, -0.8540145127885376, -0.7848989505110465, -0.7842432115618283, -0.8829633623392543, -0.7327599540493884, -0.7411146269427545, -0.8104703670810318, -14, -0.7561234777287793, -0.7657394056679045, -14, -14, -0.7413600102760165, -0.764897318399745, -14, -0.7423452436613359, -0.7472673427698867, -0.7419745546632925] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0641  total reward: -1532.099930128013
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4512866053376616, -1.4828645672815786, -1.1534289526300445, -0.9560841823861045, -0.8843270423297049, -0.8639677631460888, -0.9810280277162687, -0.8322773985399762, -0.8581311064091639, -0.9623304451337402, -14, -0.8561228713363472, -0.8802060939033778, -14, -0.9140336005724359, -0.8412074783798554, -0.8372900075198111, -14, -0.8366317829045029, -0.8542149253417941, -0.8350663686512985] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0642  total reward: -1534.2712226802014
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0895203617630322, -1.492943080636985, -1.4190844807766803, -1.520475670938443, -1.635149665561078, -1.3175352501001836, -1.3345091945870269, -1.3894663181497136, -14, -1.3615185981233768, -1.3866832386969759, -14, -14, -1.3420334596878483, -1.3592039173913206, -14, -1.3416331174634912, -1.3587525458026963, -1.3390151536484316] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0643  total reward: -1536.4213651485888
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4159033233439295, -1.467950741846721, -1.1574224904021122, -0.9612354459211939, -0.8808790401110494, -0.8600388609427854, -0.976859604149283, -0.8420050653052571, -0.8496515183755434, -0.9327769037077748, -14, -0.8502522504179921, -0.8720992784317468, -14, -0.9187374086328167, -0.8391125491546426, -0.8314100789945121, -14, -0.8340818828766963, -0.8507187050906395, -0.8326072182871896] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0644  total reward: -1538.4270040541974
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6924133896408897, -2.363250015379794, -1.4635478294701674, -1.277278307332218, -1.1790637281362155, -1.190913290265273, -1.1337443628158648, -1.2156056269746307, -1.1762902436258762, -14, -14, -1.2036570706533243, -1.2440603645118717, -14, -1.2543485720576513, -1.1366523881079356, -1.0998365761214153, -14, -1.1799967858433922, -14, -1.174228826614086] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0645  total reward: -1540.054076101372
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5266346866682013, -0.5236045545648486, -0.7490425542066471, -0.5834062066538845, -0.5293013285409663, -0.5684149318812451, -0.5359262560700874, -0.6910476939296206, -0.5261100961807601, -0.572862173683912, -14, -0.547654454052148, -0.5745140290100057, -14, -0.6821730231683321, -0.5281459243917643, -0.5267331972101451, -14, -0.530394854627409, -0.5658371004152973, -0.5272354710531959] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 0646  total reward: -1542.236679483479
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -0.8877070505547068, -14, -14, -1.4469497990992233, -1.693288439967014, -1.7357435550190596, -1.69274709868843, -1.7235750350294272, -1.674248238907192, -14, -1.6760522999971657, -1.6842328728832099, -14, -1.6927470986884305, -1.6576856439449605, -1.6848170379465464, -14, -1.6614442500869209, -1.6641860820351315, -1.6589988275422438] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 0647  total reward: -1543.9299553631042
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3988426497654698, -1.4147088370069563, -1.127851285367875, -0.918429188559375, -0.8530025744923478, -0.8406781862535332, -0.947440785673884, -0.807714128350399, -0.8241827221025296, -0.9066157027875155, -14, -0.8246379394035864, -0.8500036595671694, -14, -0.8807137843566517, -0.811355096402546, -0.8111379015821111, -14, -0.8078927363117928, -0.8306476686193537, -0.8055688290704586] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0648  total reward: -1545.4842769842485
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.305532834887991, -1.2011097155832922, -1.160564565324773, -0.8321236590130755, -0.793195417492846, -0.849210548307962, -0.9027665752097105, -0.7726382431884703, -0.7545897875043547, -0.7830376593349153, -14, -0.76154758815249, -0.780479420301687, -14, -0.8075191661702832, -0.7532749370825104, -0.7417542519419557, -14, -0.7502471919199056, -0.7696514806110137, -0.748752792073665] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0649  total reward: -1546.6800870148418
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7553689872739471, -0.8277484507538669, -0.6274335738893645, -0.503926716390499, -0.47425298510337033, -0.47883418927787313, -0.5106420273238977, -0.4668203127384327, -0.4578174563343425, -14, -14, -0.47016662920414487, -0.495754159793914, -14, -0.4944916956120643, -0.4588543092647156, -0.4515504484432976, -14, -0.45833348203290614, -14, -0.4540557786513816] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0650  total reward: -1547.5403165849475
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7095310019299496, -0.7199789085824246, -0.5822847976285949, -0.47121540141282403, -0.43361107956698186, -0.42694531023195126, -0.4853513786562031, -0.4087676730888215, -0.41789668158128107, -0.46079036804081336, -14, -0.417570621149148, -0.4292203936356596, -14, -0.44282416153802556, -0.411544858950329, -0.4087670092813661, -14, -0.40960010277794584, -0.4205245594068253, -0.40867912166238635] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0651  total reward: -1548.3560299886947
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7218381001618934, -0.6741677559850258, -0.6233381216583476, -0.4586930695841737, -0.4326735091909787, -0.4511085622097207, -0.4951066206983285, -0.41319015470625614, -0.41160766916907987, -0.43114019310110185, -14, -0.41536353569955115, -0.4268970676372704, -14, -0.4343075249852708, -0.4091294574735891, -0.403467379606393, -14, -0.4079285140670957, -0.41864180784693744, -0.40703428208490416] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0652  total reward: -1549.083806500449
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5363462956083533, -0.6136705825550971, -0.43325042480458154, -0.3672677889150833, -0.3384691193401398, -0.3324546174073665, -0.3634991598546034, -0.3355257676702194, -0.3257653899312159, -14, -14, -0.3360284673377776, -0.3530017726496489, -14, -0.35125228248776497, -0.3275311640113771, -0.3215064791113897, -14, -0.32688385870391995, -14, -0.3243091321480684] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0653  total reward: -1549.7556013740173
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6183286996304587, -0.6245866014735301, -0.46187460715768375, -0.3986179334275399, -0.37103887197646424, -0.3571267400584926, -0.4115371903608103, -0.3446519753606725, -0.3650733446423482, -0.3985181180928392, -14, -0.3589043932915452, -0.3703187571787577, -14, -0.3872318092350925, -0.35192064584141614, -0.3496688895226657, -14, -0.3512760029814745, -0.36821937201198846, -0.35028839445658827] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0654  total reward: -1550.5571987913645
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7743565233354014, -0.7922991430071851, -0.6159581267420886, -0.5222162154131565, -0.48278664715702146, -0.4690743918034338, -0.5410702820358468, -0.44933444215616425, -0.4566998786158582, -0.5075157563646594, -14, -0.46502022941880006, -0.4715852138881974, -14, -14, -0.4566981319841256, -0.4759047579246705, -14, -0.4574583770788729, -0.45983688049847427, -0.4569454419868061] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0655  total reward: -1551.5854943754402
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9870116730446283, -1.0235479586346552, -0.8239291853209665, -0.6675983544227881, -0.6126343337180213, -0.6043934131266208, -0.678720395984608, -0.5757648734953025, -0.5953462192783842, -0.653941373387023, -14, -0.594331243273042, -0.6129406831856155, -14, -0.6312113033618143, -0.5826537901602483, -0.5818892471688032, -14, -0.580447913609684, -0.5980676840944378, -0.578961141919485] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0656  total reward: -1552.9311800631212
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3158837502197585, -1.3296496813004313, -1.1093721012958284, -0.8914792362966207, -0.817005367931809, -0.8070798498961804, -0.9323685635649865, -0.7598777779537742, -0.7683894564323381, -0.8320353058416909, -14, -0.7853061728740626, -0.7992924196932806, -14, -14, -0.7709759846252565, -0.7918871415914509, -14, -0.7711874901365342, -0.7765224054415661, -0.7699208141856158] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0657  total reward: -1554.484326265619
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3408617859201437, -1.3862740275850036, -1.108294703310745, -0.9055019501381919, -0.8373884812852422, -0.826533284155666, -0.9213697805947811, -0.8020936483346761, -0.810484460655163, -0.8915455509203103, -14, -0.8119454208567823, -0.8345386917280135, -14, -0.8804364584607558, -0.7993929772529347, -0.7962757588355602, -14, -0.7949509654813106, -0.810307151285896, -0.7932684245442372] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0658  total reward: -1556.08894067766
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.331862247098864, -1.399932563701989, -1.129994241653106, -0.9412573861627437, -0.8561796668925417, -0.8370586911390164, -0.947206536469263, -0.820643794158579, -0.8310143091092549, -0.9108196215556813, -14, -0.8321273198465347, -0.859507085294316, -14, -0.909245536286638, -0.8174449125277682, -0.8174565247900524, -14, -0.8138773623239614, -0.837195511881706, -0.8113459874965769] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0659  total reward: -1558.1174337720865
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7967859921713951, -1.3697235485227695, -1.2953320072327767, -1.3197208470921833, -1.4801024241935028, -1.239636055309327, -1.2280278063031915, -1.30756238033298, -14, -1.2396977142115264, -1.2732753618366441, -14, -1.2934372969461232, -1.2259437232523418, -1.216024208513534, -14, -1.220150712947943, -1.254782657270825, -1.2171471069300257] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0660  total reward: -1560.3658001933072
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.177187411543986, -1.0365369207949702, -1.0857041779201542, -1.0702342444291018, -1.2635590651790705, -1.0646815138607062, -1.0399685126459106, -14, -14, -1.069232185772606, -1.1212965905636978, -14, -1.126464005305455, -1.0454804655957557, -1.041375492450714, -14, -1.0400147602583494, -14, -1.0323422127069424] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0661  total reward: -1562.2369045292949
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3355060695307446, -1.5368770151339401, -1.1634793438445767, -0.9464225680870262, -0.8724814927944707, -0.8762906516330482, -0.9315615325471037, -0.8584167724757904, -0.8490206661862759, -14, -14, -0.8719112808880646, -0.9227624732361832, -14, -0.9189308304457842, -0.8469158935176343, -0.832550760748096, -14, -0.8469662502374375, -14, -0.8387621232808843] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0662  total reward: -1564.0149168152025
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.644209657255084, -1.566558123083544, -1.4221384522441025, -1.063570460994885, -1.002286076673341, -1.0378501144872259, -1.1329644841783473, -0.9619702702894496, -0.9584831763668815, -1.0150700890217454, -14, -0.9642267918861553, -0.9904058186508394, -14, -1.0250614617230769, -0.951539831477856, -0.9391716529045633, -14, -0.9475521125248857, -0.9727225073605792, -0.945461525159485] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0663  total reward: -1565.6019520504965
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0377370739245741, -1.153821861725532, -0.9526800640529215, -0.7415409105935477, -0.6782190589489925, -0.6909585698877235, -0.7503524610999027, -0.6684061758646912, -0.6517196459850698, -14, -14, -0.6689537248478166, -0.7052690785448648, -14, -0.7030985869293894, -0.6560887455385052, -0.6477867126920327, -14, -0.654430511357452, -14, -0.6478635823894048] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0664  total reward: -1566.8863376492563
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0880966880141099, -1.1430645602666993, -0.8815758491518652, -0.7364191848650844, -0.6733824494009322, -0.6555767214792992, -0.7435144251939729, -0.6327987963792077, -0.6554299104372056, -0.7359020447851412, -14, -0.6518963971766935, -0.6710818206138107, -14, -0.6964856484927842, -0.6411804448410369, -0.6397797156326723, -14, -0.6382072898737137, -0.6530712375237507, -0.6365988860679286] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0665  total reward: -1568.2260806873203
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2339087896623153, -1.201005903573219, -1.0251694422429753, -0.8125958808425149, -0.7518895674410079, -0.7472755501191114, -0.8704145786956303, -0.7027363956089674, -0.707265782171871, -0.7479411395601107, -14, -0.7213477087370002, -0.7362529350241924, -14, -14, -0.7078953565451861, -0.7165800669301506, -14, -0.7086772605087808, -0.7211673510687947, -0.7069442416847111] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0666  total reward: -1570.0015591161796
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.2766568111501801, -1.0889354823154824, -1.1316507630300097, -1.1309523301013371, -1.3157736953411447, -1.108083431698307, -1.080276334571654, -1.129421878191624, -14, -1.0889307443110126, -1.114618382367067, -14, -1.1540723785883187, -1.0812061530794541, -1.0635362681483942, -14, -1.0749702170024031, -1.0990300605243417, -1.0727420332503788] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0667  total reward: -1571.9677501567628
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5202299400197423, -1.65027189274475, -1.2878606303264357, -1.0064841697838225, -0.9453202814931904, -0.9647407210388059, -1.028762438047471, -0.9265035786217459, -0.9073540761718034, -14, -14, -0.9353321184492498, -0.9805311884023482, -14, -0.9678285518540505, -0.9124669565932867, -0.8989090049053846, -14, -0.9091634836772188, -14, -0.9026547724347238] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0668  total reward: -1573.5481065183858
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1658432968410064, -1.1880481921728698, -0.957560922224512, -0.7704136533565936, -0.7193914637856911, -0.7163013767258063, -0.7904194484373465, -0.6896304091587028, -0.6949367862404845, -0.7746546180030182, -14, -0.695438474652489, -0.7134466302792173, -14, -0.7520823088044445, -0.6868381728637751, -0.6882210792165169, -14, -0.6828930224116604, -0.6974486360079247, -0.681447356717781] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0669  total reward: -1574.9008835755824
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1282465133666224, -1.1630326619354667, -0.9651783687540868, -0.7777567578229408, -0.7105692253299577, -0.7025080743199067, -0.7922911603221164, -0.6825812336841562, -0.6825831429237941, -0.7530906313117596, -14, -0.6852184556391337, -0.702658721799097, -14, -0.737368125972444, -0.6765075995564658, -0.6742286756314964, -14, -0.6724803284044877, -0.6890909513801926, -0.671329700478627] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0670  total reward: -1576.1879970530774
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.037415411634419, -1.0614585332202586, -0.8671673663945759, -0.6948825237489351, -0.6489936965436314, -0.6490211000189554, -0.710657516939232, -0.6265455894669658, -0.6273601837754466, -0.6915834049631395, -14, -0.6300484086045974, -0.6474242472631787, -14, -0.6848585924804872, -0.6205826431760713, -0.6261193472547848, -14, -0.6171123599728634, -0.6333930349217526, -0.6157837770164123] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0671  total reward: -1577.4078816914512
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0277133556038591, -1.0666588563940975, -0.842898492526207, -0.6887015431542942, -0.6376882617901966, -0.6293237622948373, -0.6997043837393117, -0.6049213363468807, -0.6196816988000184, -0.6912664382649029, -14, -0.6186796164505614, -0.6378366001936916, -14, -0.665741250938597, -0.6086053786564345, -0.6116757831368022, -14, -0.6059636085559823, -0.6203510522499317, -0.6041008613574045] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0672  total reward: -1578.9109300575194
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5557849950847409, -1.6355668264376795, -1.1897129837024945, -1.0246431717648787, -0.9487868881953918, -0.9164273234346848, -1.034713884122136, -0.8978398462002972, -0.9243613326989889, -1.0697186414682052, -14, -0.9188121910574321, -0.9417589808216582, -14, -0.9932432629179735, -0.9058840168741081, -0.912284641312128, -14, -0.9005014279238333, -0.9175789254001261, -0.8989475047106474] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0673  total reward: -1580.8107319544297
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5129671574047745, -1.8969057776208, -1.3105828238776653, -1.1388864344684646, -1.0305855264918515, -1.0171751297922078, -1.0532188468436319, -0.9979129370786641, -1.0215882851510718, -1.4541668722644898, -14, -1.0107918061977286, -1.0110786087879884, -14, -14, -0.986258095851538, -1.1291290986457578, -14, -1.0017491457446641, -1.0086358096827504, -1.0019620507100082] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0674  total reward: -1582.4412855841322
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0903413419479586, -1.0750697640053781, -0.9269368969277898, -0.7589826440616013, -0.686394798642978, -0.6686736730678305, -0.7954507452793095, -0.6444904853457237, -0.6451239622633858, -0.6645887658703896, -0.673543086481399, -0.6593480772644426, -0.6748676498525117, -14, -14, -0.6439038702043189, -0.6525476708179918, -0.6601899428526763, -0.6472906135403107, -0.6612281176855089, -0.6442955338508253] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0675  total reward: -1583.6530111367902
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9873136231634647, -1.0174382817125187, -0.7774022298200679, -0.6572804492785758, -0.6022800093653716, -0.5822571673931667, -0.6805539373446163, -0.5655002297359593, -0.570810858326378, -0.6272212182554546, -14, -0.5800965485985137, -0.5896874838054198, -14, -14, -0.5682076995592226, -0.5832786008837206, -14, -0.5686761673948363, -0.5731278528102137, -0.5678216824536727] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0676  total reward: -1584.787229548656
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9861592567620454, -1.0212844790093873, -0.8011406618847708, -0.6613554356984984, -0.6034569953659248, -0.5881106083670447, -0.6736975864015731, -0.5710844281874016, -0.579138786214163, -0.6461983048873083, -14, -0.5799716171385668, -0.5955415078250467, -14, -0.6125813279911246, -0.5733795951247121, -0.5715958451109632, -14, -0.5701087686859335, -0.5817479887494611, -0.5687181821299296] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0677  total reward: -1586.1731115713128
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2256253556489305, -1.5946190523733157, -1.0459143796320114, -0.9395037911947917, -0.8375496019555632, -0.8209664493538718, -0.8506706140824766, -0.8145500522291502, -0.8455953343758704, -1.2762749389480346, -14, -0.8246530158293509, -0.8293040472437476, -14, -0.9249596276011365, -0.8171066205765372, -0.8800556727340478, -14, -0.8169990334001637, -0.8158457614124318, -0.8171638405267996] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0678  total reward: -1587.6159638463137
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6306586497140159, -0.6276536145541542, -0.7308312541474318, -0.7094557012843005, -0.6292137745079813, -0.6265173852592576, -0.6389044427732986, -0.48316123915573467, -0.754771576443952, -0.6614211710970442, -14, -0.6410743140297869, -0.6508775076030121, -14, -14, -0.6320746250867483, -0.6743067642458449, -14, -0.6280441412844364, -0.623015574795964, -0.6283022227717497] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0679  total reward: -1589.3434837892223
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4682758303512418, -1.2557184585603023, -1.3088158780635648, -1.3144239171931578, -1.5001407599401206, -1.2811079650709625, -1.2574121996244554, -1.3018154092557288, -14, -1.2716360644306606, -1.3114070671390878, -14, -1.3584025155589858, -1.2521951833511857, -1.2418465324227828, -14, -1.2482795223134024, -1.2865188031625785, -1.2443587037529602] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0680  total reward: -1591.8155756108665
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6783785838217289, -1.4043309100059875, -1.2836849249987758, -1.2668846291763078, -1.3850968480719357, -1.2528944240450448, -1.2439301587350207, -14, -14, -1.2824005503883495, -1.3598208646587662, -14, -1.329656104690602, -1.2427004940643762, -1.2214175716214968, -14, -1.2423088236340976, -14, -1.2302452892213918] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0681  total reward: -1594.5014720432803
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.983893808690364, -1.7095825644618219, -1.5590972567689274, -1.4913162805843299, -1.7734005775981856, -1.4746515239736793, -1.493507848635013, -1.6112076449517754, -14, -1.4974954267311535, -1.5463690972525581, -14, -1.5925763534472646, -1.4747484886218925, -1.4636249210747172, -14, -1.4692485309209498, -1.5263629773502345, -1.4644788607923012] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0682  total reward: -1597.4442431243547
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0276369450617735, -1.680003876969083, -1.5448699981115015, -1.5308067388218427, -1.6731691355392042, -1.5096882145005683, -1.4972688586922664, -14, -14, -1.5349051010725987, -1.619874534730674, -14, -1.6119639053914145, -1.4955584701382507, -1.4738376002934632, -14, -1.4927600885514982, -14, -1.4791461599997762] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0683  total reward: -1600.5212078192606
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.29863011035042, -1.8468867882173854, -1.7024970836464333, -1.6820343123590076, -1.9275461719302838, -1.6072225166009177, -1.639909708498987, -1.7534471212772356, -14, -1.6453700505960678, -1.7014764777363127, -14, -1.7480844941228988, -1.61243877284787, -1.5953552800089608, -14, -1.6080261254593406, -1.6588233492679827, -1.6031270946123561] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0684  total reward: -1602.9945060567952
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9583679563812602, -0.9375557514619691, -1.0970419295397877, -1.0310550435281611, -0.8405699824291132, -0.8782284445888953, -0.878570232784738, -1.140412798942097, -0.8744364723081013, -14, -14, -0.9375218279184688, -1.0271151382953119, -14, -1.145106352235454, -0.8677274886994464, -0.8415013670622262, -14, -0.8920980200425799, -14, -0.8779429575258378] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0685  total reward: -1605.4343681781547
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2161826138271676, -1.7935186613440055, -1.5205548515718101, -1.679292328909928, -1.8257038536809294, -1.6368473177261358, -1.6167521276626915, -14, -14, -1.6491598940009664, -1.713638307260105, -14, -1.7442152850514474, -1.6277200006938688, -1.621075471986824, -14, -1.6078527523640116, -14, -1.599292138930217] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0686  total reward: -1608.372705034932
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.971823850845345, -1.5874341261548834, -1.4863891508573683, -1.4921497121828484, -1.6394605642654652, -1.4734052151584973, -1.4272153582541984, -14, -14, -1.4631009083669215, -1.524415027972959, -14, -1.5625053047525974, -1.436829188254063, -1.4213428858815749, -14, -1.4263851687245352, -14, -1.4177820052056176] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0687  total reward: -1610.9792756604106
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6496395803956467, -1.3524911967233002, -1.2493439787258636, -1.2361324365947282, -1.3892257072148984, -1.2207558066412791, -1.1963894525157062, -14, -14, -1.2306665325353494, -1.2987208340543788, -14, -1.282106647281202, -1.2045009528656339, -1.1886504204780033, -14, -1.2004290244146811, -14, -1.1887886202728581] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0688  total reward: -1613.142680254521
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6462043991808821, -1.7294176587445365, -1.318257236791169, -1.1424472891737165, -1.0323271775396805, -0.990428907011132, -1.1518415370530295, -0.9671509857721469, -1.0087597137359368, -1.1044918337135703, -14, -1.0006615165449126, -1.0355433588770253, -14, -1.0803144047985636, -0.980333788015979, -0.9737459324796847, -14, -0.97806674769966, -1.0127962909097536, -0.9747541736324722] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0689  total reward: -1614.7812559011013
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6750687648877629, -0.6698112988923787, -0.8129225597663675, -0.773119051470255, -0.6724845470014303, -0.6694598530629693, -0.6873758862330971, -0.5549255814243996, -0.7309704252067957, -0.7300103587983383, -14, -0.6953482797750821, -0.7186823960428371, -14, -14, -0.6739270743614167, -0.7162728265201261, -14, -0.6733676804362618, -0.6850936444968707, -0.6714246608081204] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0690  total reward: -1616.6542599466684
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7876826436152518, -1.5187995339571128, -1.391445340872545, -1.3495933871863455, -1.5285173180151728, -1.331991308457277, -1.3475245890312466, -1.4998124907384405, -14, -1.3487420778064731, -1.389002091338217, -14, -1.4650510542466055, -1.328055060178125, -1.3363060028777978, -14, -1.321792003659888, -1.3536331007668407, -1.3180784641426997] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0691  total reward: -1619.1650349621898
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0060531987355037, -2.108217059282349, -1.6325026036045789, -1.3934563447178174, -1.2621731537007042, -1.218094119971766, -1.404397985852339, -1.2022278144652097, -1.220248704215071, -1.3580867905830525, -14, -1.2205528225910163, -1.2519522665043739, -14, -1.3195138955151873, -1.202450486359243, -1.1943316385492284, -14, -1.1942982401125002, -1.2230216063079153, -1.192696551378657] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0692  total reward: -1622.0066189254549
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5901109442124377, -1.8303970870597603, -1.7467469728636835, -1.8884383522329407, -1.977606396574136, -1.683542349035306, -1.6637882678080953, -1.7520781034155983, -14, -1.6766254739941306, -1.720748032398385, -14, -1.7618600119628622, -1.6597125274721238, -1.6381437492456827, -14, -1.6533480017837234, -1.6865267657249228, -1.6488874118863508] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0693  total reward: -1624.704554303165
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7473990992045911, -1.9709092636816388, -1.4293772757742504, -1.1958362328166006, -1.1066499147176623, -1.0931642622922038, -1.1939167109512296, -1.0780028149903174, -1.0756008457386343, -14, -14, -1.1007233814916728, -1.1619557963435032, -14, -1.1571445634101918, -1.0714813886056325, -1.0552023800551527, -14, -1.0694123551516954, -14, -1.0597916284646003] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0694  total reward: -1627.093635028019
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9036539301007445, -1.523699873246523, -1.4172695252890726, -1.4033747856493248, -1.598258859653335, -1.3341069389782083, -1.364086342810576, -1.4725179221116784, -14, -1.3630192996159287, -1.4004929853655441, -14, -1.4443497857657883, -1.3412026323804627, -1.3263630013729875, -14, -1.33646688172121, -1.3802488000303645, -1.333878344798651] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0695  total reward: -1629.499853704655
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7467264877202213, -1.997150823751942, -1.4860121384463707, -1.2469127094210317, -1.1294889894945734, -1.1100781123126362, -1.2403378491997554, -1.0998287626420733, -1.096861344426819, -14, -14, -1.1162832473941053, -1.1728057837890578, -14, -1.185446311891866, -1.09318943371098, -1.0815698299896863, -14, -1.0890833933307078, -14, -1.0798556752631392] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0696  total reward: -1631.8054457397689
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.987459537285586, -2.191826637989139, -1.746034154014341, -1.3686645813967635, -1.2791576404231653, -1.3086882335826737, -1.382850924281652, -1.2687022151402128, -1.2335445357067216, -14, -14, -1.271580196740455, -1.3394803353803226, -14, -1.3400401184905841, -1.2395322876363148, -1.2198707313175243, -14, -1.2362911166017494, -14, -1.2257363598508129] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0697  total reward: -1633.9122226651539
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5882547450801237, -1.5216928177035294, -1.27132652312216, -0.9970497073048448, -0.941543380987138, -0.9463041382244568, -1.060918548122794, -0.8966266123636539, -0.9009637540789813, -0.9633089231864453, -14, -0.9059912630923216, -0.9310427256569879, -14, -0.9586467891992468, -0.8930605017796536, -0.8844612904030668, -14, -0.8887909838579663, -0.9141958977333647, -0.8869061940673298] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0698  total reward: -1635.5556797787776
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2677097058481401, -1.371239275479178, -1.0567961809030766, -0.8583227440919113, -0.7964844928862176, -0.7938532769013648, -0.8834843541943116, -0.7809847243368185, -0.7654619036545837, -14, -14, -0.7878313779861443, -0.8299633425214336, -14, -0.8285932472920021, -0.7690394103383114, -0.7599133149924875, -14, -0.7654490016520619, -14, -0.7589958232207514] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0699  total reward: -1637.0843615701297
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.376264589339236, -1.4702050906112818, -1.0754726985714782, -0.9426170827193637, -0.8242049808517358, -0.7775136421758143, -1.0099946978590528, -0.7722244264352544, -0.8102943952703096, -14, -14, -0.7932162173779486, -0.8284477967117165, -14, -0.7722244264352544, -0.7745783401388632, -0.7774671995045741, -14, -0.7752267249739809, -14, -0.769685968131225] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0700  total reward: -1638.519667244797
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0601841120764695, -1.1759434225771976, -0.9579389278827396, -0.7420028570588432, -0.6933518575887064, -0.715990781259234, -0.746031282361375, -0.6982695240447232, -0.6672785023197149, -14, -14, -0.6902081350475446, -0.727253653976951, -14, -0.7290572711468793, -0.6726656446261504, -0.6607153416778005, -14, -0.6714843813197939, -14, -0.6656197065360191] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0701  total reward: -1639.8310803490622
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0802149883915906, -1.140041140830021, -0.871237774776852, -0.7498312500304506, -0.6859423552242597, -0.6635746744792457, -0.7533327630588277, -0.6514724697293204, -0.672133960439297, -0.7409575443708234, -14, -0.667640765529765, -0.6873026212552024, -14, -0.7352159317834662, -0.6553696166894492, -0.6523803704483799, -14, -0.6520173670905806, -0.6724265194923033, -0.650697762587549] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0702  total reward: -1641.439401991161
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6059640469813543, -1.6887195373556136, -1.3743272136694875, -1.1120451132484237, -1.0125101845123001, -0.9993560389534211, -1.1206293252917812, -0.9528709769641129, -0.985486119682073, -1.100935446565558, -14, -0.9802352883717979, -1.0065819564908667, -14, -1.0487381282859634, -0.9642952397171264, -0.9576469929276394, -14, -0.9593019033719294, -0.9817063281040193, -0.9576238795110799] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0703  total reward: -1643.5031984456577
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8587075578992236, -1.911692712987674, -1.5487793059188777, -1.2799955599617405, -1.1744247291616643, -1.151124808299365, -1.3232391691721266, -1.1024451851996737, -1.1159003263347635, -1.2136161496730073, -14, -1.134865517634444, -1.1556355182732723, -14, -14, -1.110546296308641, -1.1481894114051405, -14, -1.1131690442457378, -1.126194755415868, -1.1109254775327388] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0704  total reward: -1646.19306008068
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2179422756164016, -1.8152735604039627, -1.6793196523907101, -1.651717701746486, -1.85677910953147, -1.595717949697364, -1.6231566199133503, -1.8290931064687896, -14, -1.6210477179083163, -1.6641965160322876, -14, -1.7433268307215182, -1.5996433398653036, -1.5940949445239305, -14, -1.5908854896228952, -1.6168042668860565, -1.587416449822756] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0705  total reward: -1649.4527262715173
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3768041875840127, -1.9090680648442389, -1.7667666185223592, -1.7575132847046575, -1.9609344408560512, -1.7072182211320248, -1.7006837531534904, -1.8501902082756612, -14, -1.7125680029506694, -1.7688971774816327, -14, -1.8556748088782848, -1.6846790529974942, -1.6922054190003395, -14, -1.6780088358201857, -1.722199108004113, -1.6722497410144335] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0706  total reward: -1652.8207599138036
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.455612771182139, -1.9221144578119205, -1.7974398075703153, -1.810015476741273, -2.033590654491874, -1.7388449824066934, -1.7192068689564581, -1.8192404934326567, -14, -1.7372245633225492, -1.7880070677296716, -14, -1.8651238828612549, -1.7075588360522178, -1.688465107139608, -14, -1.699015035889757, -1.7468580430298568, -1.695783901271948] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0707  total reward: -1656.7349989729385
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.6263158145777297, -2.237060775552028, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0708  total reward: -1661.9415164224501
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.477318029910563, -3.185016988198511, -14, -14, -2.9760086600420483, -3.074270626987771, -14, -14, -3.031289985160776, -3.1245371952045886, -14, -2.9760086600420435, -2.9548528465020345, -3.0030923681771085, -14, -2.9842333585068923, -14, -2.9694566739596717] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0709  total reward: -1666.152429771863
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.392011885632146, -1.9568315804998984, -1.8167465983543403, -1.8056554086080994, -1.9852932448536118, -1.7617270018004727, -1.757711625215999, -14, -14, -1.7886123588286533, -1.8716888424042548, -14, -1.8829001655451532, -1.7534997012260714, -1.7361278935587463, -14, -1.746778498283283, -14, -1.7335953195023974] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0710  total reward: -1669.3343073872775
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.059723114617174, -1.6095646802156929, -1.5054971816714522, -1.549213906901272, -1.5942534497863567, -1.4947773599760499, -1.4568235102454317, -14, -14, -1.503628818293154, -1.588647074348283, -14, -1.572412432519416, -1.4597103199738701, -1.4322738722875838, -14, -1.4620183185532623, -14, -1.4482822959117896] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0711  total reward: -1672.0005471711484
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.694997003401691, -1.4450960409301707, -1.3088244674490765, -1.2607570819039735, -1.4710236899054134, -1.2380680971799272, -1.2649210451668331, -1.3675405596529278, -14, -1.265917971360513, -1.3095049383486372, -14, -1.3592907495936488, -1.2418865165208712, -1.235616726655962, -14, -1.2380235856393464, -1.2849234488929495, -1.2339659115833859] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0712  total reward: -1674.966156891655
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3080120749513013, -1.9998979909764223, -1.7845413780573556, -1.7562853604121036, -1.8298332254726746, -1.7224402957355123, -1.789235411587077, -2.618371903969804, -14, -1.7483467217833712, -1.7614259463430695, -14, -1.9318863633937713, -1.736768413288764, -1.8440981005244144, -14, -1.7316905961428088, -1.727984002181911, -1.7316438089232973] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0713  total reward: -1678.0365602018132
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.878943515977333, -1.570878755577445, -1.4299896595529593, -1.387742684218982, -1.625648970100283, -1.3324753311810997, -1.3465209040789872, -1.4784619331978983, -14, -1.3742096716026948, -1.3948450281145932, -14, -14, -1.3482914335307712, -1.3949523585984598, -14, -1.349298735775539, -1.3626180903706187, -1.3479630144228785] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0714  total reward: -1682.0444657233343
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.7724290917265257, -2.668850356521705, -2.9340152245337103, -2.7014427878467555, -2.8529913050252333, -4.115733015782356, -14, -2.7043415294556814, -2.7290636550116503, -14, -2.7014427878467573, -2.6852147625187657, -2.7330780870834492, -14, -2.6759794588534263, -2.682743368190805, -2.6754301903399598] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0715  total reward: -1686.9917286880136
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.3468200649823485, -2.2568815353637244, -2.3762637714710224, -2.2709942103390404, -2.3520195735090343, -3.469526921735953, -14, -2.3012957079498726, -2.3135562519309807, -14, -2.555270038741259, -2.279321653539923, -2.4313823373924617, -14, -2.2777195802209884, -2.276145689081138, -2.2784126081574354] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 0716  total reward: -1690.707450220917
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1269450332167428, -1.688954175742195, -1.5420948355630153, -1.536583497959701, -1.704835438560882, -1.4535801620829731, -1.4987358023346928, -1.6536898119984436, -14, -1.4906382479924236, -1.5306719500748474, -14, -1.5936024501827426, -1.4685589110311899, -1.4568834645560707, -14, -1.461846134378983, -1.4982257071546734, -1.4588399975398272] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0717  total reward: -1693.4827752924737
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8666672159792663, -1.5178644227113172, -1.4000291581512943, -1.3796692829984631, -1.583964238433278, -1.3069440930273244, -1.321824576826156, -1.434495076891511, -14, -1.3484451535776476, -1.3742389385354246, -14, -14, -1.3228178769957608, -1.3628611177975598, -14, -1.3247303347492259, -1.3334010977192188, -1.3217449094735667] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0718  total reward: -1696.0956083498268
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8598014081850893, -1.4739544805157143, -1.3827991701264755, -1.3848464271497727, -1.5469124098923646, -1.325437583783549, -1.3296107830447816, -1.4327687409639591, -14, -1.3358118022636734, -1.3782759152831545, -14, -1.4382998073769824, -1.3153233999290095, -1.3015004330241244, -14, -1.3101515036461309, -1.3323423035145892, -1.3058889643257199] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0719  total reward: -1698.6353266085353
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7236392319422547, -1.4226700838120747, -1.3054110195194601, -1.2831006965881335, -1.4865074879664706, -1.2628098930152045, -1.2552786392502258, -14, -14, -1.2805691929369567, -1.3449725880142442, -14, -1.3542774814199208, -1.2557308027392182, -1.2472605439849516, -14, -1.2485140411142255, -14, -1.2382178256843455] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0720  total reward: -1700.8692882565124
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6517640506108884, -1.8374706988866845, -1.3071848350848594, -1.1118824835656953, -1.039241034519384, -1.0217713391967411, -1.1170063238654093, -1.0278637935381632, -1.004338590140378, -14, -14, -1.0362317350853107, -1.0987576683283102, -14, -1.0937383962504421, -1.0064595162933376, -0.988202611391828, -14, -1.005901843166899, -14, -0.9957438222928654] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0721  total reward: -1702.9697390785961
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.3257497120703838, -1.1273058628668688, -1.1705463252261643, -1.178912196130922, -1.3732885776775023, -1.1600365031782607, -1.1194386516462655, -1.1453046174818968, -14, -1.1342925273113051, -1.166282131430485, -14, -1.2088830882895156, -1.1188437218029474, -1.1016438138483162, -14, -1.1148173095244696, -1.1481865213383695, -1.112248210692073] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0722  total reward: -1704.8158895757028
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2730614702857346, -1.3920018337169, -1.0044440718952599, -0.845939646508084, -0.7823154407756095, -0.765295881813875, -0.8659981365265974, -0.7603127547071473, -0.7515408044362827, -14, -14, -0.7719771570551645, -0.8110952921519137, -14, -0.8042713468818846, -0.7539880877882805, -0.7446277814146486, -14, -0.750329810020958, -14, -0.7445066832583159] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0723  total reward: -1706.205538227383
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0482622999670284, -1.1588775228578359, -0.9014194900036752, -0.7280035274024367, -0.674361489069687, -0.6768915619545492, -0.7367016318160617, -0.6677321723480333, -0.6497520629438951, -14, -14, -0.6706666494593192, -0.7087223483143219, -14, -0.7076168974710362, -0.6531300289023191, -0.6431266983146773, -14, -0.6510997224554479, -14, -0.6451419684217641] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0724  total reward: -1707.5099004250314
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1197687163237744, -1.1534945355725639, -0.923373431443144, -0.7592012235303459, -0.6989946700968128, -0.6865528397121655, -0.7741752719511173, -0.6659118746901465, -0.6763648502031097, -0.7546675025902536, -14, -0.6766152639255748, -0.695381394276311, -14, -0.7300464502271162, -0.6666565259687254, -0.6647572974127504, -14, -0.6625952977533391, -0.6770111260642989, -0.6612354993337569] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0725  total reward: -1709.011454068158
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4405330666627316, -1.4642236127265809, -1.2151276821523738, -0.9584904177969706, -0.8890345834407922, -0.8906071417291429, -0.9852464175989896, -0.8449639136102722, -0.8578445569714855, -0.9479321810589518, -14, -0.8576417305924056, -0.8793113112530595, -14, -0.9171468766350024, -0.8466262270925354, -0.8401349766036796, -14, -0.8418488084810188, -0.8580303882268641, -0.8403181437928695] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0726  total reward: -1710.764718661922
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.508319434034173, -1.6710442472880713, -1.2291374544377671, -1.0299022717877222, -0.9549715058141021, -0.9419086850873194, -1.040868299051705, -0.9463831726128161, -0.9183738574797785, -14, -14, -0.9525540015700131, -1.0135844142011987, -14, -0.9977106944097937, -0.9242779009371853, -0.9073796857076972, -14, -0.9230694068404139, -14, -0.9131296171603748] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0727  total reward: -1713.104749609397
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9684132203137001, -1.78136944572059, -1.5336110847690332, -1.4372145832357954, -1.7675766967857045, -1.428010171039616, -1.520557358559785, -1.6237302542524008, -14, -1.4732087219430179, -1.5337543903541235, -14, -1.4280101710396165, -1.431088068303598, -1.4201771796395228, -14, -1.4400911032016506, -1.5334273520717612, -1.4326512617672078] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0728  total reward: -1716.2818625137797
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.582430509063763, -1.9782278883243642, -1.8519324614229848, -1.8983211626558674, -2.107115071210937, -1.801975031065876, -1.770714222146539, -14, -14, -1.8102942023975026, -1.8882656825949338, -14, -1.901761583207404, -1.7818326160759748, -1.7691792910057211, -14, -1.768879765609219, -14, -1.7569357247431483] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0729  total reward: -1719.6113830971449
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2193016785302113, -1.7782174775384638, -1.6472435500228968, -1.6548992029288583, -1.8075728063329646, -1.614558732724407, -1.5846026715568102, -14, -14, -1.631682237759668, -1.7133302233303147, -14, -1.7040449374516895, -1.591566619465404, -1.5702059973385736, -14, -1.5843263871127904, -14, -1.5725848586221765] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0730  total reward: -1722.6844848380072
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.085355681532312, -1.6910561492548146, -1.589609008570665, -1.575328458761396, -1.759283813646545, -1.5255397530361585, -1.5296318245227625, -1.6971729048147308, -14, -1.5330228896610423, -1.5732492109980638, -14, -1.6545409676778513, -1.5150875536231314, -1.5130751089055046, -14, -1.5062511964848926, -1.536430479916074, -1.5028957435235597] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0731  total reward: -1725.9270210419713
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.467851229973054, -1.9763930681125548, -1.8448288874687533, -1.8318809315894637, -2.068154355803855, -1.7620138225475692, -1.7688801860036816, -1.906099908166828, -14, -1.779669042799974, -1.8336133133918262, -14, -1.8967696578781639, -1.75249825449309, -1.738723022801605, -14, -1.7444293233695842, -1.7835443011572885, -1.7396404604406053] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0732  total reward: -1729.6414357800395
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.867750832639527, -2.2412263746921717, -2.0695007280331503, -2.105833470638865, -2.2832597205009297, -2.0426177337229734, -1.9865328672490004, -14, -14, -2.0440782712021264, -2.1407503291093666, -14, -2.147333864911429, -2.0013167273897703, -1.9756352207861945, -14, -1.9899638947711291, -14, -1.9756917152666869] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0733  total reward: -1733.1766036929391
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.095399115549895, -1.776715384885336, -1.643376335354574, -1.5996295594394891, -1.7900640663521536, -1.557374889457539, -1.6079594062025189, -1.8256715151124419, -14, -1.6021240738321476, -1.6473346263456397, -14, -1.7404987162170098, -1.5712124257149627, -1.5798335848824923, -14, -1.5623568416777793, -1.5943967333723572, -1.5595326921134016] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0734  total reward: -1736.0650581829743
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.829415613751078, -1.5273268123257295, -1.4079947411757667, -1.3732286096172315, -1.5783750704375972, -1.3402385034690787, -1.364167617876176, -1.4807184404436617, -14, -1.3629243622292373, -1.3931615964418338, -14, -14, -1.3301000126904015, -1.3799080160257629, -14, -1.3358490420013356, -1.361641245614769, -1.3310796005776395] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0735  total reward: -1738.636094311968
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6972935885657032, -1.4542015709105238, -1.3187849183465759, -1.2658805913537594, -1.4960722874774688, -1.2452742882834222, -1.2488422812574467, -1.3130620969309132, -1.2919755698827928, -1.2701413138759536, -1.2921069060386157, -14, -14, -1.2401340689158853, -1.2599690679945557, -1.2626774799176785, -1.244604951998608, -1.259424533624903, -1.240936116303264] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0736  total reward: -1741.1732844152423
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.789428564971363, -1.460636151269599, -1.3748331326940046, -1.3551135828453384, -1.5502853640181484, -1.3053161155310102, -1.3246688896181271, -1.4426067635502586, -14, -1.3246474467365694, -1.3513728993849725, -14, -14, -1.29679516958318, -1.3304084767697242, -14, -1.3010987773382165, -1.3213941955815283, -1.2970560343584139] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0737  total reward: -1743.9796085459718
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.143981371475936, -1.716782403672277, -1.603029155078115, -1.590494675211431, -1.818014600994075, -1.503058375228, -1.5074712264256709, -1.5998566408766213, -1.5527006872386162, -1.5440966253255672, -1.5673204288051243, -14, -14, -1.5079921197419022, -1.546387852880152, -1.5280321462897233, -1.5131003182935692, -1.52527777715484, -1.509528961146368] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0738  total reward: -1746.9116437974042
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.029458599559948, -1.6763296558361824, -1.5077495405180918, -1.4762745132717539, -1.6337721347181864, -1.4161080435991849, -1.4703085163874463, -1.5733730854275667, -1.5068142041723551, -1.4677015655163699, -1.5084045203304404, -14, -1.5816468298464146, -1.4185882390450937, -1.4427969748132683, -1.4658217899549493, -1.4349078584977553, -1.4611116750833053, -1.4289768762043307] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0739  total reward: -1750.1706581412557
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.609300680754149, -2.1046922692942274, -1.9584779913057788, -1.9327302211577404, -2.218934716280002, -1.83453070391099, -1.838868352679861, -1.974502085791119, -1.8899986951625034, -1.8778188158987537, -1.9015615342716794, -14, -14, -1.8416496056090197, -1.884197978844289, -1.8589309265608456, -1.8466132493142848, -1.8575691433564194, -1.8429063002522885] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0740  total reward: -1753.9633029283182
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6757864892689014, -2.330026128008314, -2.0266437548144967, -1.981081452863291, -2.099944344857635, -1.924446538517244, -2.0308370458981533, -2.6718300103585624, -1.959881561314278, -1.9846713212097762, -1.9973939324363938, -14, -2.1784266623095645, -1.953603014936161, -2.038781671502935, -1.9448331041994351, -1.9587445434165747, -1.9599786993146677, -1.958114083151497] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0741  total reward: -1757.0521206700269
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6036251229996374, -1.3448554957259549, -1.2401245372464482, -1.198051063460442, -1.4082879227684655, -1.1691856023650902, -1.1680915160307388, -1.242684778746966, -1.2047802593557337, -1.1894879855741483, -1.208185441678496, -14, -14, -1.1641455252315536, -1.1892608237807176, -1.1824498390374054, -1.167518304364926, -1.180976985000277, -1.1643712031915165] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0742  total reward: -1759.9767696192741
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.329319149557538, -2.033813647127675, -1.8109599620258714, -1.7812081938848026, -1.8526054477602503, -1.7742068257913328, -1.8415811131984992, -2.591656475097693, -14, -1.775990071256802, -1.7777287686210352, -14, -14, -1.736118828023839, -1.9250795163812795, -14, -1.7606500439346995, -1.7673092863849353, -1.760503424015691] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0743  total reward: -1763.0035551678723
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7904452094347298, -1.5308292031156636, -1.3669051638008232, -1.315784967501651, -1.5296704289107093, -1.3017937059985216, -1.3077162009221335, -1.398373949614687, -1.3410629622850097, -1.3222590220538, -1.3450078779682784, -14, -14, -1.2930111414631316, -1.3167038105956232, -1.3131702386769026, -1.2949798718714298, -1.30387859834109, -1.2906667205742162] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0744  total reward: -1766.075097923378
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4876181525318564, -2.0460994539796626, -1.888869739042966, -1.8486810269260372, -2.1205237917373565, -1.800891469553733, -1.8107482988609886, -1.8996862747797625, -1.8628574078385327, -1.821171049762661, -1.8528975392081684, -14, -14, -1.7811277532427476, -1.8110829224519176, -1.8142712300535446, -1.7865259978134158, -1.8182567590121972, -1.7808760349315695] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0745  total reward: -1769.4865432460222
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3637271428022664, -1.888756290277489, -1.734805035026728, -1.7144451110069214, -1.98489318363808, -1.6149274489587884, -1.6219655510932829, -1.7075292301197906, -1.6800122593053692, -1.6667402702354293, -1.6934330848739454, -14, -14, -1.6281632247200122, -1.6737822392915207, -1.6497501088756512, -1.634864687727951, -1.6491047198514481, -1.6305692877126112] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0746  total reward: -1772.4285467687923
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8536657022349199, -1.5354275673070377, -1.4061481726881797, -1.3718070857853986, -1.53901368809516, -1.3238295573270775, -1.3560128148587585, -1.4610044393009989, -1.39147281174412, -1.3589657259363717, -1.3921822929837875, -14, -1.4482063359276858, -1.3161452677747856, -1.34258251997525, -1.3567833479388067, -1.3315497487843706, -1.3574519476448206, -1.3270760738113299] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0747  total reward: -1775.0323264732988
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.836153174292209, -1.4728701448356734, -1.3638411849543988, -1.3533984243789356, -1.5246451234629341, -1.3043229571588353, -1.3116788419883032, -1.41022835757294, -14, -1.315298009846908, -1.3540452728054226, -14, -1.41423159846788, -1.2970240170939513, -1.2843407210951148, -14, -1.2911456071956262, -1.3247379993506951, -1.2876344367318726] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0748  total reward: -1777.7089346918747
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9686387162554586, -1.5374752651615176, -1.458170857187728, -1.4925143636347022, -1.5853090758901487, -1.4242791406887845, -1.4048515991708213, -14, -14, -1.4389817108820988, -1.5099031480125342, -14, -1.5067036071365352, -1.4081857971885319, -1.3899415526719858, -14, -1.4035862039205167, -14, -1.3922674974806961] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0749  total reward: -1780.4449858157293
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8667222584000496, -1.5477174494371748, -1.4277900467383224, -1.3919206851893877, -1.5945341375709232, -1.3518943380656177, -1.3750212466875094, -1.517080762438538, -14, -1.3772369546808576, -1.4179474290026923, -14, -1.4679170434796467, -1.3558541130580428, -1.3492469433161, -14, -1.3495659468762897, -1.3797790026735395, -1.3461095711825684] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0750  total reward: -1783.495201568294
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.382504353220605, -1.9599921400466032, -1.8030250097257885, -1.766495689224692, -1.9846715884527155, -1.7018472120041024, -1.743977965867698, -1.9903586665455202, -14, -1.737986294799704, -1.7773487310318854, -14, -1.8472847639882666, -1.7171391606630877, -1.7170521115501065, -14, -1.7063974580070602, -1.739136285412532, -1.704106181382163] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0751  total reward: -1788.5273587073727
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.246310311913685, -3.3265207487013058, -3.426207052196567, -14, -3.389936377512103, -3.4467663348562305, -14, -14, -3.3416055328158967, -3.373822360071882, -14, -3.3335888327963925, -3.3684312704790904, -3.3303099270746643] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0752  total reward: -1794.4005407752452
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0297317132086388, -2.775033363364626, -2.753709828497607, -14, -2.6575974319557196, -2.6854179225752963, -2.9233104603081186, -14, -2.6856067161109745, -2.771542414173757, -14, -2.922043520406937, -2.646225024390452, -2.6234578683444085, -14, -2.635995961716856, -2.6898946268936186, -2.626871755958665] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0753  total reward: -1800.1169013815656
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.197614879479242, -14, -3.230193555558467, -3.0987718636836394, -14, -14, -3.1974386336628013, -3.3727743763317735, -14, -3.352069955004394, -3.1191339154865534, -3.055901754734529, -14, -3.1238296640585355, -14, -3.0929027379761185] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0754  total reward: -1806.4840172029349
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3400031298363855, -3.3716116223453314, -14, -14, -3.3767830479103496, -3.4644744694156078, -14, -3.6012159575315805, -3.3361964014383108, -3.313701735645933, -14, -3.318282063139544, -3.3861784591239665, -3.3112140666347574] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0755  total reward: -1813.1964111706393
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.39467945922263, -3.4933357440357122, -3.806394370494163, -14, -3.47868799693756, -3.5871626526032716, -14, -3.7281541618787317, -3.424083718861995, -3.39917275031783, -14, -3.4117358703556477, -3.515457770682286, -3.4011799010694785] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0756  total reward: -1819.655556080292
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.1523617575205702, -14, -3.086080025695979, -3.137446677741772, -3.4817380150405617, -14, -3.1313212741867305, -3.190420294718974, -14, -14, -3.062036406883723, -3.185586441905472, -14, -3.0729856242468956, -3.1196761471865715, -3.064465450430156] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0757  total reward: -1825.9758251065978
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0758  total reward: -1839.9758251065978
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0759  total reward: -1853.9758251065978
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4796433400951017, -2.907798927076533, -2.3671343228484654, -2.5679050454907366, -14, -2.4825877156379597, -2.559337128691326, -2.793829678301648, -2.651483300065247, -2.5707605279583814, -2.640927070716533, -14, -2.6669352964159043, -2.489404968098425, -2.516353996952831, -2.5834382932672364, -2.515854921870415, -2.591890204322151, -2.507509425812494] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0760  total reward: -1858.8623270482913
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.9306969846278514, -2.6715195713539166, -2.6398948388111028, -14, -2.5082018320119293, -2.57094801256497, -2.7441080894546217, -2.637344884195887, -2.57525767084809, -2.632520515047713, -14, -2.720371196480639, -2.5002448079352533, -2.529425275856402, -2.5834583020213806, -2.52644674320257, -2.567377099207863, -2.5193676188450365] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0761  total reward: -1863.6098506037893
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.160846481581357, -2.5969638826561647, -2.3818590407378224, -2.3331164324288665, -14, -2.266761861321025, -2.2976680829054077, -2.473855821012374, -14, -2.3024877897470963, -2.3721529672372133, -14, -2.480190933732454, -2.2626053076857837, -2.2412322762777412, -14, -2.252295455695046, -2.328983051395909, -2.247278747562606] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0762  total reward: -1868.7775937066667
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.0091396255123994, -14, -2.998888771698136, -2.957382594698953, -14, -14, -3.039904664330581, -3.2017096851359086, -14, -3.194902426600711, -2.9614031115465163, -2.920745774206879, -14, -2.950652622678727, -14, -2.9265108265998236] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0763  total reward: -1875.561660600676
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.878961500026817, -14, -3.821265010639575, -4.029443127151121, -14, -14, -3.9084080596281328, -3.9398723545483865, -14, -4.358830452525069, -3.872166163475899, -4.135270932006705, -14, -3.8637335091009772, -3.8598532188845076, -3.863321119802549] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0764  total reward: -1881.7683419232003
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3445617510738, -2.756299203284928, -2.5139487762605945, -2.4716532205126023, -14, -2.3946683702809692, -2.4350032630720277, -2.686323787889775, -14, -2.4466351236838597, -2.495265273201469, -14, -14, -2.379286758987105, -2.508774652278638, -14, -2.391848569643362, -2.4246611733740844, -2.385416311884516] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0765  total reward: -1886.4113682995635
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.215857793642644, -2.6491467166691245, -2.396715533456388, -2.342482445193705, -2.6757539733195754, -2.2825305092416652, -2.292699475682176, -2.44915228131179, -2.344813568784159, -2.3114603525958275, -2.349176998902787, -14, -14, -2.2652936501477043, -2.316140773208249, -2.2967180559641336, -2.2709916929333187, -2.2977275420843095, -2.26373961737616] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0766  total reward: -1890.7541104476932
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8184197568806404, -2.45188859509783, -2.2000510215882025, -2.1083442039972735, -2.4439994320761573, -2.106264348841372, -2.122205063651362, -2.2915996409837263, -2.1559807622316054, -2.1244244514633714, -2.157600827635488, -14, -14, -2.082988428312971, -2.136393627388734, -2.107681511302096, -2.085326161124082, -2.1121715417900107, -2.0790025307535305] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0767  total reward: -1895.018164141035
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.969017010800637, -2.5930414972081564, -2.310185673304031, -2.2128242816374977, -2.5634346607789062, -2.20411956265015, -2.218007673685158, -2.4073619762558347, -2.2521794094319825, -2.235255656352421, -2.2684388947865584, -14, -14, -2.1862994926351798, -2.256135556669228, -2.2053373693557967, -2.1908665752842347, -2.2135799327821792, -2.185051162588173] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0768  total reward: -1899.5923006042099
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0959491948791613, -2.7834968866747642, -2.483635534748687, -2.398887971883734, -2.58777909919168, -2.449271847999335, -2.5441916464013405, -3.143385361795582, -2.406184810081993, -2.4196506519735013, -2.4280310472379925, -14, -14, -2.42155347041606, -2.5032007229984936, -2.3906101806842117, -2.3915525860108224, -2.388046932143658, -2.389085300587061] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0769  total reward: -1903.5234478491948
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2046691553951248, -1.8030755939644751, -1.6475160267978268, -1.6031068730989197, -1.9303316004675308, -1.5640548290725835, -1.5891222899363269, -1.615057911302852, -1.6740519843083492, -1.5654474587490765, -1.5820840039447932, -14, -14, -1.5454712143491616, -14, -1.621997348395932, -1.5437963099252425, -1.5227189318121996, -1.5431003128412009] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0770  total reward: -1906.3772561445492
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9343144452616337, -1.5151901838283361, -1.4162168089948113, -1.41805475868249, -1.617239483822798, -1.3205271960683316, -1.3250393737528596, -1.3857250496331486, -1.371317094645528, -1.3575266555519643, -1.3752657621407833, -14, -14, -1.3287329947246933, -1.3484460418088542, -1.3477194562492876, -1.3334465663835384, -1.342957172778793, -1.331089363542107] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0771  total reward: -1908.690570972843
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6994102267829072, -1.7206096355757754, -1.392608781722695, -1.132681142862914, -1.0502119363983857, -1.0363603740852385, -1.142128407531372, -0.98634280751042, -1.017806799779807, -1.0936832557318439, -1.0446475548923635, -1.0158979480608012, -1.0429163064688984, -14, -1.0888695035773146, -0.9850887120343834, -1.0010002056656617, -1.0150308726778954, -0.9971629880934338, -1.0118797233077133, -0.9927876322256665] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0772  total reward: -1910.1795498795882
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5176247840182733, -0.5116068179656823, -0.6444097785705531, -0.5950134678658354, -0.4990752248072853, -0.5038348815985954, -0.5054814618397653, -0.6229244058180724, -0.5054090063486991, -0.5131079596357232, -14, -0.527963212877421, -0.5565973942978264, -14, -0.6927560649260162, -0.5059584347863961, -0.5107335134624357, -14, -0.5073216426214663, -0.5420534242056221, -0.503890194710525] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0773  total reward: -1911.9096923841266
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.855259294660021, -1.8162675526046923, -1.6831868062124449, -1.4056077476765103, -1.167549095289831, -1.266956489094056, -1.3806969226347383, -1.2354946567332012, -1.2569437946543125, -1.463681925974505, -14, -1.2602709690333775, -1.2981087196965866, -14, -1.3330925250247407, -1.2430071751173049, -1.2283749532854003, -14, -1.2336932203212752, -1.2598289282335218, -1.2310672797314495] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0774  total reward: -1914.7356984676994
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3539337595692627, -1.8905438427262509, -1.748969111942595, -1.74228768480287, -1.918364411055451, -1.6656055237526104, -1.700000563586533, -1.9176281584812376, -14, -1.6971583531188488, -1.7467265692095633, -14, -1.8364623599386072, -1.67142113132717, -1.6760154558708005, -14, -1.662916353150299, -1.6934357468704464, -1.658456988282802] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0775  total reward: -1918.6504814684854
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1027695378704387, -2.591441719507804, -2.399385150960084, -2.3269832739320058, -14, -2.265251530586083, -2.302575994261028, -2.5229723002078255, -14, -2.3037837153752645, -2.370354322681513, -14, -2.4458454966338543, -2.272636451565857, -2.255808529292932, -14, -2.262086083129013, -2.3323287080604964, -2.256326012503072] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0776  total reward: -1922.933058391587
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.780684818745626, -2.331065593180563, -2.1182572684266545, -2.085529326745871, -2.3204981856092877, -2.09915320441051, -2.0384454428897305, -14, -14, -2.1138691946180628, -2.250421199689929, -14, -2.21217249081438, -2.051360530994517, -2.0174533376292803, -14, -2.049298759652749, -14, -2.026768393808952] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0777  total reward: -1927.5723702361188
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0623086486809856, -2.7691382875566144, -2.703941308944398, -14, -2.6343694645254647, -2.682357437657028, -3.0250628237484434, -14, -2.6840719820911136, -2.7551633842116003, -14, -2.8837325100208897, -2.64262203489357, -2.638473554894998, -14, -2.6264634166557266, -2.668715918197001, -2.6218585069021474] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0778  total reward: -1933.30011816485
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.116280406350964, -3.163672448346797, -14, -14, -3.176859117599829, -3.2644556009095744, -14, -3.340364215451798, -3.127723776300332, -3.1021499117906104, -14, -3.111924455766103, -3.189063984283047, -3.1058894218291333] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0779  total reward: -1939.6498049096408
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.33328793246052, -3.2703438492961956, -14, -14, -3.362451208928721, -3.5455144822053852, -14, -3.5085497342034953, -3.2936671293717175, -3.256533760742046, -14, -3.2782347335372704, -14, -3.247536833000377] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0780  total reward: -1945.58887532018
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8676472050092494, -2.991048869169348, -2.8089525686903776, -2.9027233404603767, -14, -2.824631482563831, -2.7021162662368794, -14, -14, -2.795730142372631, -2.938831982514536, -14, -2.9741700242437483, -2.7240978713888593, -2.68488667743354, -14, -2.7119704069723416, -14, -2.6915335775387588] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0781  total reward: -1952.098415021915
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.852098146177557, -3.9146670326642927, -14, -14, -3.8589016429572034, -3.875224196249883, -14, -4.289194157704136, -3.8221553141400917, -4.109161158133915, -14, -3.823111713921805, -3.8250378746196008, -3.8246530243013277] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0782  total reward: -1958.2438182522628
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.282306883969771, -2.7008272761018617, -2.45610332072662, -2.407372006935087, -2.6788042183811203, -2.323744115023975, -2.3768310064343834, -2.5324332744875835, -2.4419379549595313, -2.3872687794482377, -2.448105836260929, -14, -2.5668488860322496, -2.3060967031768946, -2.3489611059192486, -2.3766825519454895, -2.3305536348642164, -2.379690069272755, -2.323247916207676] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0783  total reward: -1962.6631895024495
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0443324786738684, -2.4259983619532552, -2.2280613312355717, -2.227387677552723, -2.457515747954736, -2.1402598919152442, -2.1608407130940313, -2.356114783475264, -14, -2.1683438418902394, -2.236060046038119, -14, -2.3605933663421697, -2.1289742257267807, -2.1222092222432245, -14, -2.118811297807722, -2.1662943950251936, -2.1132745470099996] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0784  total reward: -1967.6828655408729
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.935472246158115, -2.9477240919615544, -3.1715448477000914, -14, -2.957880910544594, -3.0330445256932372, -14, -3.11574594748256, -2.924828075699603, -2.896012156673502, -14, -2.913070508637294, -2.9805809668387715, -2.9064014914132916] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0785  total reward: -1972.5442145318536
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.696370411867524, -2.196610640743351, -2.042953506913682, -2.055390487838891, -2.170216521621281, -2.0429325480667804, -1.9776232438264154, -14, -14, -2.040500077460915, -2.1587235147090187, -14, -2.1629466188061723, -1.983358773239143, -1.9463773342155526, -14, -1.9849082504402773, -14, -1.9653368343073554] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0786  total reward: -1977.185809359757
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.685758572113492, -3.0476497674638496, -14, -2.795096700096124, -14, -2.680710302607885, -2.7765493409747295, -3.1549712840053505, -14, -2.7586597684515097, -2.833941243851292, -14, -2.9616951204186894, -2.71412281616918, -2.7085991116441774, -14, -2.700874942281227, -2.7469508129199234, -2.6952174936877284] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0787  total reward: -1982.7834284713936
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.0663445692985634, -14, -2.906790291224518, -2.9285217023409, -3.1857472707346974, -14, -2.972614320547575, -3.021403165223649, -14, -14, -2.9193465454485543, -2.9818666335459847, -14, -2.921605153292478, -2.9612299944286153, -2.9169088090286603] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0788  total reward: -1988.1149691273117
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5002872242689107, -2.7850902892719573, -2.571919964393406, -2.558257793233916, -14, -2.4706895507481983, -2.462547505035143, -2.6251220188595217, -14, -2.4827260502410273, -2.5596565117253065, -14, -2.657138921000736, -2.441818045739866, -2.4201791144077824, -14, -2.430937461609434, -2.50504473609699, -2.42475036469359] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0789  total reward: -1992.428072145874
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7503177939376244, -2.1790153128916097, -1.982802629039118, -1.9991682699311553, -2.2096843645494055, -1.9747519840699592, -1.9007896084167162, -14, -14, -1.9677752334006915, -2.0632181011621453, -14, -2.0745554833048017, -1.91919733601479, -1.8964712938757975, -14, -1.905374632630136, -14, -1.8929239041545016] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0790  total reward: -1996.3341041023875
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.70791449351624, -2.2666930146215236, -2.0969472130806865, -2.075001850115165, -2.229663898517907, -2.0457792473539484, -2.0386430307112935, -14, -14, -2.084075892665178, -2.1888109445116197, -14, -2.177681831645652, -2.029039854264455, -1.997223646889227, -14, -2.0293255765711877, -14, -2.0131080523589273] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0791  total reward: -2000.2642674846338
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7159327464259806, -2.20935032946023, -2.0376215946409983, -2.017883853804641, -2.2351906608477745, -1.943574685468932, -1.9824526795766475, -2.204305442957506, -14, -1.980496478068541, -2.0384010642044617, -14, -2.1502957307838435, -1.9478606160290814, -1.9535845961881912, -14, -1.9375311354147822, -1.9874456965674798, -1.932939735357126] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0792  total reward: -2004.2635332180414
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1041037590192175, -2.336115192132823, -2.1409230782184405, -2.245393827002304, -2.212974874402779, -2.0950278623106313, -2.0980859440805233, -2.8819845787535283, -14, -2.081036799756331, -2.0911617664184394, -14, -2.270742054016504, -2.0752419945063862, -2.1732625623802426, -14, -2.065720425542502, -2.0604179449059377, -2.0663259980506634] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0793  total reward: -2007.326031471622
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7773812223919645, -1.7184206319563313, -1.3644826920747883, -1.174298191202161, -1.0703213111661278, -1.0219115538963437, -1.3421107193597508, -0.9838978981478799, -1.0668690657414523, -14, -14, -1.0165793581464093, -1.028225332923758, -14, -1.127901279091415, -1.000476878761403, -14, -14, -1.0027132913947638, -0.9686184096824628, -1.00208030867462] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0794  total reward: -2009.1015907547614
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3324061739740898, -1.3874254521969778, -1.1318745859568307, -0.9307113754631254, -0.8516182217541939, -0.8376155277470558, -0.9421831714215595, -0.8207184770157808, -0.8230497435994372, -0.9090339901759628, -14, -0.8283037451125597, -0.855243141411819, -14, -0.9005700152577311, -0.8137440584798414, -0.8152381072268237, -14, -0.8093404427205987, -0.8247372983838474, -0.8069408734569433] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0795  total reward: -2010.7628432853378
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5426224561325914, -1.573538517390864, -1.2198223886838961, -1.0523951233078732, -0.919893717394601, -0.8663167131742048, -1.0859852659751952, -0.8476018665904788, -0.8946802024331416, -0.9322791906326009, -14, -0.8757237069292755, -0.9103934819617437, -14, -0.8476018665904786, -0.8509958819033402, -0.845511379388726, -14, -0.8585355458138624, -0.9177514547670481, -0.8543116571194207] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0796  total reward: -2012.2746317431645
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1149174015773207, -1.2239237992374923, -0.9035381263729066, -0.7404264204064381, -0.6961361610974043, -0.6953693451262741, -0.7497406146439926, -0.6868658731994778, -0.6705074252062909, -14, -14, -0.6912281947277913, -0.7305089743467603, -14, -0.7233500988687237, -0.6732094171143379, -0.6608172610552252, -14, -0.6727858239561478, -14, -0.6662770784378363] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0797  total reward: -2013.7580745911362
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4116615522357012, -1.4365415745791021, -1.1469583875510492, -0.9498905507384037, -0.8719737919234949, -0.8509312487828872, -0.9760522209118763, -0.8336003883088908, -0.8378399561670943, -0.9095885552029033, -14, -0.8413705526591994, -0.8680477802464628, -14, -0.9038691841625007, -0.8287427717015988, -0.824241882579436, -14, -0.8252661951984779, -0.8457798239805447, -0.8226255869166905] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0798  total reward: -2015.912574367828
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.590289297565289, -1.3494512125169502, -1.4004203252674934, -1.4143878846969378, -1.634286361129175, -1.3876006334293738, -1.3420355643988602, -1.3716294990354327, -14, -1.3603637012252043, -1.3992846921665594, -14, -1.4555881738711225, -1.3407083750065447, -1.3199983204671668, -14, -1.3347185253489169, -1.3779536954746214, -1.3318741897751294] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0799  total reward: -2018.0563903554446
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8541693636381822, -0.8428908552200751, -1.0278698503634829, -0.9214765308681397, -0.8116195677774646, -0.8339467597247604, -0.8232490178389029, -1.0895476109597113, -0.8195596996071048, -14, -14, -0.8735464396864787, -0.9454704114835901, -14, -1.1142131902736823, -0.8287509834266433, -0.8182359422451758, -14, -0.8347114406489651, -14, -0.8238176671492314] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0800  total reward: -2020.4264085710986
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0507795472840513, -1.755344340719928, -1.4983988829791064, -1.5966981844261365, -1.742566036630575, -1.6095441018448342, -1.5734601842966378, -14, -14, -1.614017372564518, -1.7034301773859695, -14, -1.7203723696552293, -1.58847234635549, -1.5691724276243708, -14, -1.5735294200387269, -14, -1.558398647876614] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0801  total reward: -2024.3972400976922
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.022154309136954, -2.65620697187324, -2.5285814037857413, -14, -2.4810385007172475, -2.6101029455344786, -14, -14, -2.5422375966296213, -2.644094610506895, -14, -2.4810385007172466, -2.4792079061259478, -2.4978820871104563, -14, -2.488010923023197, -14, -2.4724326436144826] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0802  total reward: -2029.3169060324367
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.8740520936409113, -2.44891080649508, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0803  total reward: -2034.1094746151334
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.0854208142658015, -2.461561909520799, -2.345419851411838, -14, -2.409957879969449, -2.360502048054348, -14, -14, -2.4150528599009915, -2.512840965335474, -14, -2.542000640237697, -2.3979702426147926, -2.387925814001049, -14, -2.3575790991658097, -14, -2.3436577762019106] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0804  total reward: -2038.2977862720277
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9896619007593936, -2.338505579284103, -2.1811579895467075, -2.2500638855885957, -2.305893351131426, -2.19927082047014, -2.1127349674027527, -14, -14, -2.181543385291982, -2.307499928327112, -14, -2.320067430089592, -2.1213581077997152, -2.0792078778051297, -14, -2.1241240009000038, -14, -2.1028908426282453] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0805  total reward: -2042.1840285099365
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.548503062385181, -2.088178951245163, -1.9106254912671718, -1.8777166368682057, -2.1231175653347902, -1.8197748736872528, -1.8502499769122296, -2.0382067746919725, -14, -1.8499819691691382, -1.9040314035893497, -14, -2.001920307216129, -1.8211423324226643, -1.8059840634747923, -14, -1.8112285599984426, -1.8495654610748395, -1.8070343601035834] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0806  total reward: -2045.6487324951781
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3886841460453625, -1.8547005688092102, -1.7337274143710897, -1.7806879457854712, -1.8927018709051373, -1.7224574800488552, -1.6684981982682894, -14, -14, -1.7221175527903552, -1.8027724008586627, -14, -1.819478792024627, -1.6790355712629752, -1.6569910672063048, -14, -1.6692110931680992, -14, -1.6587199217671087] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0807  total reward: -2048.483278080511
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.5773280324619148, -1.4027077598069964, -1.2434601165495172, -1.1866361855670156, -1.3703853310970715, -1.1743185659693804, -1.2105788357600764, -1.3747019137031156, -14, -1.2085681484789441, -1.24580475857932, -14, -1.2938841361024092, -1.1868316390287124, -1.1946293227007905, -14, -1.1806344481508626, -1.2072717710150351, -1.1775545181260911] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0808  total reward: -2051.1457008463735
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2067518323944784, -1.6760497778813197, -1.5787345265361277, -1.6169859578168861, -1.8014551615436252, -1.4754332576157942, -1.486817723421312, -1.5867348171704456, -14, -1.517583138941032, -1.5443306239204613, -14, -14, -1.4904501507157306, -1.5164521452413777, -14, -1.4905951733815312, -1.5054189524584238, -1.488104199893589] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0809  total reward: -2054.171314174927
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.195094218426695, -1.8038622802264352, -1.6444891717165597, -1.606927666480342, -1.8450709503553009, -1.5695643141152067, -1.576621104840046, -1.7308098103918645, -14, -1.5848508496309897, -1.6269356029335154, -14, -1.6898045142911058, -1.5621898885875614, -1.5538181430495417, -14, -1.552799225677186, -1.5921445149170435, -1.5501800709376463] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0810  total reward: -2057.8092077626798
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8669363756325748, -2.5729980905687637, -2.2463210913644436, -2.0978195090516163, -14, -2.073911840806774, -2.1920335918699556, -2.305987564250934, -14, -2.144077955141979, -2.2224936028151303, -14, -2.0739118408067743, -2.0840019758949397, -2.0679579119001157, -14, -2.0953601618133852, -2.2225216094361437, -2.0877135168148957] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0811  total reward: -2061.5502136217265
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.336428766514796, -1.9203156085746138, -1.7453790936508016, -1.7356156683465387, -1.8950448710215535, -1.7276436791268583, -1.6846682128681594, -14, -14, -1.7360371411084874, -1.8310248896774257, -14, -1.8262483776240765, -1.691943232577918, -1.665763220318656, -14, -1.6881000178087335, -14, -1.6730479471464257] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0812  total reward: -2065.553362141062
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2239082792486435, -2.6410325102616614, -2.4102723297172264, -2.4290507941397546, -2.4655042774517804, -2.355087071120029, -2.39720544464196, -3.444284905200231, -14, -2.3591453384403875, -2.3721024571200178, -14, -2.6400066694703614, -2.344921912342468, -2.483008381268608, -14, -2.336578617767094, -2.3319158166671885, -2.337385299016956] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0813  total reward: -2069.2016376399765
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8416783812221047, -1.5503140197763674, -1.400173613678145, -1.352096417618418, -1.7165983895355412, -1.2939533488350061, -1.4024830405523905, -14, -14, -1.341220057426059, -1.3535488383944472, -14, -1.4939559514451164, -1.318975596093152, -14, -14, -1.3160273856852014, -1.279337278834524, -1.3163596822473942] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0814  total reward: -2072.1603841985925
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.264934635052635, -1.9124113882481708, -1.7835874774504679, -1.7259259814010768, -1.998878890654546, -1.6796527442568898, -1.7202353417431513, -1.9091465334511284, -14, -1.7129840577776032, -1.7611060366592495, -14, -1.8310235071548298, -1.6918844692543045, -1.6767183263728496, -14, -1.6838295044286835, -1.7259026914760218, -1.6794092797815374] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0815  total reward: -2075.249064053423
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9154783690607449, -1.6150320199028316, -1.4799762886059753, -1.44997060851865, -1.6293187486591896, -1.4557421474703343, -1.4194293290705533, -14, -14, -1.4644075046672678, -1.5498953317745268, -14, -1.5260804843783622, -1.4293627710918209, -1.4060432238305993, -14, -1.4266277577369613, -14, -1.4119615284576577] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0816  total reward: -2077.591093155207
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5977686915359164, -1.6397482887692323, -1.3068426182374635, -1.084741189357129, -0.9918998087355643, -0.9667977744525563, -1.1090134584797924, -0.9408493166807165, -0.9575325822737825, -1.0475856980562706, -14, -0.9581880304248045, -0.9891823139763046, -14, -1.028363616810466, -0.9424569970172597, -0.9387589399811558, -14, -0.9389993056865542, -0.9663586615378792, -0.9359858779534556] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0817  total reward: -2079.452527746621
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6444704515010973, -1.757194927952496, -1.2577855362032517, -1.1513146908105127, -0.9931237485549803, -0.9269314682326261, -1.1539583103743218, -0.9215139529067081, -0.9801063897579817, -1.051935544112039, -14, -0.9515120569574422, -0.9881271030252345, -14, -0.9215139529067083, -0.9231635076522914, -0.9168578371002235, -14, -0.9293603969867849, -0.9815289369961597, -0.9254487134603493] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0818  total reward: -2081.013952977968
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0105649912068768, -1.1729248551703635, -0.8719514223746789, -0.732227633568642, -0.6698918697418315, -0.6637755572024692, -0.7173457390865927, -0.6663185428613443, -0.6510996869366024, -14, -14, -0.6690356719779742, -0.7099911407005137, -14, -0.7139922410871422, -0.650933811751959, -0.6395396677885863, -14, -0.6517771096786813, -14, -0.644567394247328] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0819  total reward: -2082.450746588601
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1674513077892084, -1.5420622594191407, -1.0763218747227994, -0.928239450228059, -0.8161424563218507, -0.8094323478729943, -0.8321729430494719, -0.7949389349202018, -0.8236674793476102, -1.22402260609014, -14, -0.8037242629846748, -0.8085634435402411, -14, -0.8975922577047006, -0.7976054860907588, -0.85408000655646, -14, -0.7972237080546659, -0.7957833038229676, -0.7972539428441701] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0820  total reward: -2083.9207623584603
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9943885121216081, -1.2908030707784677, -0.8711386712091909, -0.7847393884184195, -0.6926211165791559, -0.6781172334894477, -0.7110000505424647, -0.6725024255003438, -0.6892895804470032, -0.975592514105546, -14, -0.6805326149713249, -0.6815844505775168, -14, -14, -0.6645411918424033, -0.7590671446238862, -14, -0.6751106475177653, -0.6787674994449323, -0.6750768349389028] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0821  total reward: -2085.2051678671082
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0641879265945293, -1.0807434935718525, -0.8724123826339001, -0.7122280280186165, -0.6568379044350748, -0.6455381992939434, -0.7340708133732047, -0.622544062218715, -0.6246806002662525, -0.6653159897658069, -0.6396217445263559, -0.6337875667796448, -0.6433507162815874, -14, -14, -0.6199137993646038, -0.6349251464984089, -0.628220223170648, -0.6214588063393761, -0.6280549386912102, -0.6198643168057666] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0822  total reward: -2086.757875908457
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.647838822772838, -1.592828220154563, -1.3331407488309996, -1.061672903034535, -0.9915224838117334, -0.9851334862646735, -1.1261214219868034, -0.9359758470958746, -0.936227658510127, -0.984314672147647, -0.9690735300851704, -0.9514412222445436, -0.9666808128712537, -14, -14, -0.9325990327184496, -0.9476935536801434, -0.9502018562771031, -0.9354996341575271, -0.9488248766868145, -0.9328437245430615] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0823  total reward: -2088.755139706608
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8219076103176208, -1.837598692706707, -1.5249805793716609, -1.2364231200038114, -1.1305809874010155, -1.1111009813091248, -1.2959413576658778, -1.0589581833657045, -1.06705146464825, -1.1540214258815207, -14, -1.0862043409104547, -1.108408876135798, -14, -14, -1.0659150409204121, -1.09752297490868, -14, -1.0674241889911646, -1.0871562281392626, -1.0646647654324295] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0824  total reward: -2091.070560026829
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.08612664869198, -2.1646188198340854, -1.7669293064518503, -1.4609591534432693, -1.3287674621258758, -1.299860607522745, -1.48146814385466, -1.2642448339713965, -1.2883458913765955, -1.4121892842218264, -14, -1.2883094098747012, -1.3287254094610341, -14, -1.3958455303910984, -1.2654419197611952, -1.2617506126319176, -14, -1.2596555313629887, -1.302957842471011, -1.2564621368552757] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0825  total reward: -2094.5163295951074
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.433313965424612, -2.48743308907095, -2.3313955186337747, -2.4443662743652563, -14, -2.202996440347063, -2.2177332390843363, -2.3103220083590283, -14, -2.2261144453320902, -2.2826961050846326, -14, -2.3114424870081303, -2.19759142899607, -2.163600061974837, -14, -2.193955288448743, -2.261051893245516, -2.189307431423271] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0826  total reward: -2098.1828285125557
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1849221624362363, -1.709928227138567, -1.5739883887732407, -1.6002300375725427, -1.7409953738120094, -1.5399364961679614, -1.5183141084380483, -14, -14, -1.5584094571128229, -1.6428476972359776, -14, -1.6387231895631997, -1.521872094512266, -1.5052566653235058, -14, -1.5164020370499902, -14, -1.502898855473188] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0827  total reward: -2101.5007313961432
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5081525476019935, -2.1984292306581517, -1.9454452848084702, -1.8338515123228043, -14, -1.8208353146351033, -1.9082887487729054, -14, -14, -1.8698687994499505, -1.9480380701750164, -14, -1.8208353146351028, -1.821937693501112, -1.8326396809800076, -14, -1.8266472469293544, -14, -1.815004028114622] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0828  total reward: -2104.6872448335694
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9058397542729064, -1.523003795828811, -1.4377822138765866, -1.452503351081045, -1.5909108797247324, -1.4456621564387169, -1.3732303224908724, -14, -14, -1.4267535398931694, -1.5082567240483717, -14, -1.500587647712495, -1.3895823950848538, -1.368835549723644, -14, -1.3841251653468427, -14, -1.371509409311426] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0829  total reward: -2107.58292780044
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1405740001785496, -1.740196313062646, -1.6126248567093038, -1.594718108035678, -1.7760364022174198, -1.5394099068565519, -1.5604117522008338, -1.738838008455801, -14, -1.5639203220328808, -1.610017543977525, -14, -1.6862875111087299, -1.5387722672164044, -1.539383515362749, -14, -1.5307529200652819, -1.556790924945789, -1.5268474171467858] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0830  total reward: -2110.5195081100783
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.060235333706935, -1.591396496316654, -1.495264285706683, -1.5161746447770956, -1.68705985400598, -1.42390995012149, -1.4353508705164515, -1.5245416282835944, -14, -1.4401559764191263, -1.4852216792327155, -14, -1.5349359132048253, -1.4184215901972104, -1.4001036407866674, -14, -1.4142553287841908, -1.448987314907242, -1.4097328924914367] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0831  total reward: -2113.0597797344058
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8963698634934518, -2.110236954649601, -1.5611147403840282, -1.2638724136194681, -1.1890625409687294, -1.1969748643592903, -1.2670496400058389, -1.1687197767031285, -1.1484259090327842, -14, -14, -1.185192914140308, -1.2520313012281608, -14, -1.2299471929455013, -1.149559571594148, -1.1281907329997196, -14, -1.1505830712294818, -14, -1.1401679835411573] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0832  total reward: -2115.2750971564883
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8458236526294465, -2.0107150580196165, -1.4572123763407638, -1.2665367393037206, -1.1473778541646267, -1.1029420020765746, -1.2533515374177184, -1.0752874651535538, -1.1240621225788399, -1.3155041982109688, -14, -1.1113023069287922, -1.1423962696233452, -14, -1.1888723045711016, -1.0953171311545251, -1.100848360927958, -14, -1.0900355575475913, -1.1082830374183485, -1.0871266890826115] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0833  total reward: -2117.5629614870195
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6832634264363375, -1.4083101292349922, -1.286928861359286, -1.2478692320820546, -1.4588484480308268, -1.2228197749433667, -1.2414362540144974, -1.3618270501942222, -14, -1.240005547549554, -1.2640092046297662, -14, -14, -1.212485174358382, -1.2453488454518966, -14, -1.2157574339194515, -1.2384637120569164, -1.212576865377523] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0834  total reward: -2120.601422759529
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.152506774522611, -1.8618889653731983, -1.9241025523901494, -1.910271653402636, -14, -1.7650773206476218, -1.8197177165035123, -1.8501546539021176, -1.867434448792127, -1.8541198754763328, -1.878486569325056, -14, -14, -1.8197365068748061, -1.8697118626036358, -1.8380267124138716, -1.8298189410317796, -1.8439693436372242, -1.8259760981516726] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0835  total reward: -2123.2238516790753
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8657010552875507, -0.8570781184305437, -1.1254914817322357, -0.9869100773156739, -0.8566121791590618, -0.8678168791622468, -0.8606957464702957, -1.1088684168532403, -0.8565850129743824, -0.8818097152378488, -0.9464587596198942, -0.894731209956765, -0.9322964095378287, -14, -1.151115786721952, -0.8552376110204669, -0.8638205353480849, -0.9009713122933406, -0.8628642068780616, -0.9007738205355967, -0.8573515988984141] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0836  total reward: -2125.2354967366055
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9505859889964021, -2.0340630836808455, -1.6350725532746022, -1.3340312057443713, -1.2223005449318454, -1.203605879063455, -1.3511945596126236, -1.159150525061624, -1.1850715034367134, -1.3161171735105008, -14, -1.1853127493320985, -1.219342113994957, -14, -1.2720053995128624, -1.1650432802580295, -1.161826048355099, -14, -1.1588324814615982, -1.1842226316790823, -1.1564074465096557] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0837  total reward: -2127.509253205681
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9082027736068277, -1.9286405452538304, -1.6169821920054426, -1.286503058538295, -1.1842282736980287, -1.1775965464629041, -1.3266898667777975, -1.1261911666779192, -1.1385066823057692, -1.2487489658380366, -14, -1.1432087109556077, -1.177531011566368, -14, -1.2159290830875153, -1.1259523615744655, -1.1225408954176332, -14, -1.1202930408169172, -1.1499956289324884, -1.117349022565817] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0838  total reward: -2129.771505367949
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9320518653731267, -2.060648565905696, -1.6001223920261847, -1.338059080851017, -1.2109155518323433, -1.1772536884294, -1.3385146590718844, -1.144133425680998, -1.17375706702894, -1.3209594082185117, -14, -1.1696475102540553, -1.2034130496953197, -14, -1.2513767287728164, -1.1535593276032174, -1.15251316995761, -14, -1.1481131660135115, -1.1725569784785952, -1.1449031397021925] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0839  total reward: -2132.545424371204
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4893234772876127, -1.8717215942130856, -1.7352393185043054, -1.7749527925360375, -2.0393704295070525, -1.6003986734291848, -1.6230496610361063, -1.6938801183999344, -14, -1.6546564418365692, -1.6825270500868068, -14, -14, -1.6342529061797628, -1.64039280785675, -14, -1.6321457972193747, -1.6561529674369542, -1.6297855775736425] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0840  total reward: -2135.778539423693
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.186774445901624, -1.8761295590285219, -1.7239510231941009, -1.6652763193119113, -1.8832584901298144, -1.6179400984922399, -1.6872878825888216, -1.9209083725369638, -14, -1.6762922922146732, -1.7264400258814105, -14, -1.794138623470162, -1.6443996536147307, -1.648088302221662, -14, -1.6367439324598911, -1.6654788278251307, -1.6327163790602524] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0841  total reward: -2138.729129834177
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9835826681408608, -1.5327260842092836, -1.4154385094361484, -1.4275728578780849, -1.63179328944712, -1.3171949720147536, -1.3292193002771706, -1.4044773122654166, -14, -1.3605227336002705, -1.384988490443058, -14, -14, -1.3349126502475561, -1.358240624869005, -14, -1.3345080889364593, -1.3560815681951133, -1.332650311991855] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0842  total reward: -2141.3974618467214
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9725781773650457, -1.5810770265557286, -1.4347145825172263, -1.41489134986946, -1.6155577992759942, -1.3457122299003876, -1.3850854929655356, -1.4971713677204581, -14, -1.3808470925312832, -1.4203896303279617, -14, -1.4605936955133103, -1.3587492374691927, -1.342276334380019, -14, -1.354200777120227, -1.3977716562664189, -1.3511370405295353] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0843  total reward: -2143.8064000916934
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8431566605704417, -1.9817630710968384, -1.4944819867896222, -1.2059944593089764, -1.1224861974210627, -1.1179660314292177, -1.2482224824974337, -1.0902511643977277, -1.0727778781091015, -14, -14, -1.1018222660849446, -1.1552554097765453, -14, -1.1377720595771346, -1.0802863747711722, -1.0665044323251418, -14, -1.0751984379821562, -14, -1.0666619105919322] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0844  total reward: -2145.8135209201837
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6049431932300342, -1.6529039341326903, -1.3608028683737454, -1.0956774081372755, -0.9977954708818859, -0.9835110067494018, -1.1183242204018276, -0.9437335562665544, -0.9597292562633608, -1.0481991588132675, -14, -0.9612256504822778, -0.9917212210274319, -14, -1.0184372179349053, -0.9471563211294569, -0.9419113305045796, -14, -0.9438628508696435, -0.9676004690414702, -0.9406163961652598] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0845  total reward: -2147.8386999071427
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.86911526585264, -1.902831468005095, -1.5249934233919273, -1.2548110331482254, -1.150446189479224, -1.1244765317817538, -1.2893393435546554, -1.0836857659599923, -1.1120427408969071, -1.213034657692308, -14, -1.1097702999661656, -1.1449218219183177, -14, -1.1839642706159683, -1.0915216069840348, -1.0847123863912609, -14, -1.0878671673290734, -1.1241152547933708, -1.084562590793687] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0846  total reward: -2150.541055148775
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.302072433464513, -1.8798708852063701, -1.7200682722005562, -1.6832956538456272, -1.9681840164195952, -1.6083994451946337, -1.6206023890290653, -1.7609722582472687, -14, -1.6517918036736536, -1.6817493343436258, -14, -14, -1.6207184963611951, -1.6535658830477, -14, -1.6216547426883923, -1.635864404104586, -1.6186694756717686] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0847  total reward: -2154.085547384221
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.839190248351472, -2.236113035564884, -2.056166653840536, -2.051503758008696, -2.3412793440017654, -1.987809901433969, -1.9587505939890733, -2.046139230043616, -14, -1.9810628222736513, -2.043371401713142, -14, -2.1118767786071873, -1.9484583769641781, -1.9231835072911563, -14, -1.9413477282449212, -1.9979743361227391, -1.9360927902520833] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0848  total reward: -2158.1808078709864
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9452719640527882, -2.503050979719032, -2.2688578086586833, -2.22224045574446, -2.4732687211010944, -2.2117758052242107, -2.2050125872287385, -14, -14, -2.2470478468229653, -2.3753274800392514, -14, -2.378874014356132, -2.1979401217357535, -2.1681778079606353, -14, -2.1951365606003965, -14, -2.172076979473762] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0849  total reward: -2162.6428247012823
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.181289437753043, -2.695418257455061, -2.4257607644714305, -2.346214301109725, -14, -2.2729096574023804, -2.3674201173562657, -2.6562926531303814, -14, -2.3485020976216684, -2.419713131252417, -14, -2.5066359832379224, -2.3100267604835367, -2.305881649379927, -14, -2.3002167102279474, -2.365720471134535, -2.293839022335549] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0850  total reward: -2167.7639632781706
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2243367478887968, -14, -3.005523894073768, -14, -2.811642350965165, -2.8459527986437028, -3.1420158324186307, -14, -2.8988699394958535, -2.9413208648849456, -14, -14, -2.850803014805764, -2.94092293953824, -14, -2.8515746824165835, -2.8677325786403656, -2.84822891948589] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0851  total reward: -2173.104658524261
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0005162345850445, -2.690729837074577, -2.602902303653511, -14, -2.5551520949759734, -2.575773108530322, -2.7181925146989934, -14, -2.589018274887856, -2.673432302998451, -14, -2.753102179101564, -2.5447612693358015, -2.5106118436872116, -14, -2.5363210845713158, -2.6354829395577895, -2.529052895125253] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0852  total reward: -2179.5650629087413
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.967100247360514, -3.8036085365516583, -4.089586483668166, -3.9708088706219966, -14, -14, -4.0516044432710006, -4.208865641110996, -14, -4.300230143339233, -3.8414987471166384, -3.7092355376039365, -14, -3.9753467126057505, -14, -3.9497925407928527] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0853  total reward: -2186.9326952338483
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0854  total reward: -2200.9326952338483
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.152307123983571, -2.5821579122654814, -2.1512402793833134, -2.3601300828750365, -14, -2.2936952181287222, -2.3087653593773663, -2.4969546882153266, -2.398462139325785, -2.3250034044573487, -2.383785043401157, -14, -2.451507832484417, -2.2532308026709247, -2.2845073701262026, -2.3282099800668585, -2.2821071801614696, -2.334566270791705, -2.2744547303725495] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0855  total reward: -2205.161026258731
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9945366297682794, -2.3440704704170723, -2.201958250208851, -2.216670708489871, -2.4249545180708147, -2.093313588417005, -2.109488989506482, -2.215353741449574, -2.1812799418571722, -2.125890304648336, -2.1724488699559683, -14, -2.252548243641585, -2.0617222639973534, -2.0911112623334995, -2.124427012296414, -2.0820019566599584, -2.1289872152876557, -2.0770907454989693] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0856  total reward: -2209.1911554199037
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7188151520258947, -2.3027734563806694, -2.0870576907299396, -2.014737838648721, -2.3279813686471162, -1.9654377359542692, -2.0181786260303727, -2.2477320447943283, -14, -2.0098971546925437, -2.061518314539863, -14, -2.1449111965608485, -1.9832622509614113, -1.9686765068032213, -14, -1.9717775528011983, -2.02806476179521, -1.9684068971755395] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0857  total reward: -2214.0118712319963
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.8527927723440993, -2.864498723695746, -3.1058700394936882, -14, -2.9055352706410997, -2.9569682891027402, -14, -14, -2.8587082914683966, -2.9103204010326786, -14, -2.8615617477052253, -2.894689785359864, -2.855278076138175] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0858  total reward: -2219.292371871825
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4888266367873966, -2.811440531915115, -2.5728713473553753, -2.53996275974049, -14, -2.4325604867091317, -2.481993942325841, -2.7310992626757975, -14, -2.477373239817779, -2.5477105531547677, -14, -2.6399280708144315, -2.445871147159951, -2.4309091450304887, -14, -2.4341158843206183, -2.5065226918796686, -2.427707867484821] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0859  total reward: -2224.216781344917
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5247539625685382, -2.8673910669896627, -2.6369046732509616, -2.6046931353304195, -14, -2.499094373016628, -2.5663037092606187, -2.8298746109362223, -14, -2.5601509277508088, -2.643888720040463, -14, -2.7674397098783814, -2.5141963739877315, -2.512429715431217, -14, -2.5046323536052575, -2.5757322008353754, -2.4967016056072757] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0860  total reward: -2230.042314696015
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -3.5576096790972462, -14, -3.3048365794633803, -14, -14, -14, -14] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0861  total reward: -2235.2469614980655
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5909118808697764, -2.1619467694134444, -1.9766132194571586, -1.960190618719347, -2.1181760208591722, -1.9443515569438405, -1.9223743180487571, -14, -14, -1.9785028919137333, -2.1002645495752703, -14, -2.0788704470636716, -1.918075870852175, -1.8840767735106412, -14, -1.9196314066806428, -14, -1.899810222586944] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0862  total reward: -2238.906972285817
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4471849517871345, -2.060254264183871, -1.8793724444311781, -1.8240609565606833, -2.0910931331395486, -1.7869566739404286, -1.8180734623258936, -1.993447118193499, -14, -1.8224316365505038, -1.8787981217585346, -14, -1.961866669986598, -1.7891509365609244, -1.7888914465878325, -14, -1.7801265384375415, -1.8376655131850324, -1.7759340142409654] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0863  total reward: -2242.775507526043
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9896854571089775, -2.440228282670501, -2.21637975341971, -2.1740187478904285, -2.465777353435015, -2.1207164188020924, -2.125536052854098, -2.3601137550535354, -14, -2.1380293040485734, -2.188286343273505, -14, -2.275357912729924, -2.1088817772520603, -2.111476264160939, -14, -2.094880713984806, -2.1458159438212623, -2.0926012259846454] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0864  total reward: -2246.618356022849
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5264700036352274, -1.9770630406928629, -1.8508307709319656, -1.8670204015998577, -2.0497726105195144, -1.766563794604368, -1.7836403819326847, -1.9535196902757677, -14, -1.7892743072901598, -1.8394190833062278, -14, -1.9139693040864685, -1.7632644120829373, -1.7573241665573471, -14, -1.7543884691508924, -1.7914400840546296, -1.7502472708219992] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0865  total reward: -2250.159234308329
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.525891921016136, -2.076274521520634, -1.895032378904514, -1.8558762067656434, -2.0988253174272735, -1.7752167610944374, -1.8473061788961764, -2.0444967602376853, -14, -1.8287978310760693, -1.8839691435787171, -14, -1.9568211482889537, -1.8019783417808972, -1.7886402308394844, -14, -1.7962937755985515, -1.8462014507447868, -1.7906310146574844] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0866  total reward: -2253.249447844548
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8196588220743009, -1.5089900465086206, -1.3956566446225331, -1.3607072659639095, -1.587444773490777, -1.314055146551202, -1.325805917978958, -1.4509700020732106, -14, -1.342332269358025, -1.3673058653855037, -14, -14, -1.3148103431506166, -1.3519384175900706, -14, -1.3179328964932435, -1.336830512242433, -1.3149967751242573] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0867  total reward: -2255.933005731009
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9266100322864919, -1.5469499490751577, -1.4513317560681356, -1.4416417793781908, -1.620215519681044, -1.375045945933687, -1.3995787223033014, -1.524468185240557, -14, -1.3981148680796565, -1.4386803482931678, -14, -1.4944843025560346, -1.3795373989284576, -1.3698977043910392, -14, -1.3732828444491743, -1.413941916736778, -1.3695027399100137] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0868  total reward: -2258.426878579286
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.941571074099236, -2.0164024340730635, -1.5573057376330393, -1.3030128766072384, -1.1915251640903088, -1.1570223039775835, -1.324502375072424, -1.1230828132010549, -1.1533359745757275, -1.2670781819385437, -14, -1.1511569211957646, -1.1848879411568294, -14, -1.2292340972278968, -1.1312961883168178, -1.1245486196159546, -14, -1.1270400117949793, -1.1557384039810952, -1.1243701083671473] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0869  total reward: -2260.861003334703
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7559827360165452, -1.6121841662431975, -1.3855228056026465, -1.312186460350789, -1.5519549603890685, -1.3111519948050678, -1.7965618823142666, -1.5343909871745127, -14, -1.361359221883017, -1.4137789666667027, -14, -14, -1.3098048521922117, -1.3070912625209088, -14, -1.3275722148381746, -1.414351591867315, -1.3110419422157253] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0870  total reward: -2263.950380651251
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5047139274108288, -2.0043921853527116, -1.861379973308265, -1.879988269619949, -2.0269295183548257, -1.7268469320148871, -14, -14, -14, -1.8405588670532105, -1.9318188726079522, -14, -14, -1.7713747552275843, -1.737590632579407, -14, -1.7973271574947718, -14, -1.7822860540272525] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0871  total reward: -2268.0368797557303
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.367634799980543, -2.732265185902814, -2.488565018208905, -2.461857779807916, -14, -2.4376758316565303, -2.3750683290668846, -14, -14, -2.4345117445687, -2.5479326821534714, -14, -2.5730708096823784, -2.395949595587048, -2.3770439141062796, -14, -2.3777148747064745, -14, -2.3596521724645036] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0872  total reward: -2272.911008358702
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.545262008737648, -2.860238951465196, -2.6331256394512996, -2.6344185549695287, -14, -2.5779376550997606, -2.5370029008227166, -14, -14, -2.6035131659840776, -2.73910952609191, -14, -2.7315062391540015, -2.544145865772704, -2.5144538146382627, -14, -2.536187749428878, -14, -2.5144764305070133] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0873  total reward: -2279.0077440586692
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.5648236898436148, -3.7803027636252096, -14, -14, -3.6733076372441307, -3.813123210928575, -14, -3.5648236898436156, -3.5807753579904746, -3.5485376460370173, -14, -3.599048781919707, -14, -3.5822818853293086] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0874  total reward: -2285.7447644186004
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.410893714045514, -14, -3.3134397857622284, -3.2080367794168185, -14, -14, -3.3036729006900725, -3.476332806322492, -14, -3.5055587969333404, -3.2287325509533114, -3.1859877188661145, -14, -3.215667765400244, -14, -3.1884827138939436] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0875  total reward: -2292.3891933016957
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.4481180036703067, -3.5491276383476316, -14, -14, -3.536050552176683, -3.6437251575385083, -14, -3.7713549540974296, -3.4855720204866056, -3.486392793923457, -14, -3.4695930538371176, -3.5203866855120447, -3.458441164229486] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0876  total reward: -2299.105874561158
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.242674302648389, -3.2687947818312777, -14, -14, -3.325109874869268, -3.375448888734721, -14, -14, -3.265080446992175, -3.3641589700732473, -14, -3.27313323486863, -3.2974480820701073, -3.2685632557915274] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0877  total reward: -2305.6421656044386
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -3.5573675194909415, -14, -3.291559011657319, -14, -14, -14, -14] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0878  total reward: -2311.6018311059115
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.650151072625004, -2.951566677615238, -2.8036540452543295, -2.8113260892652123, -14, -2.8002123943090047, -2.6790061157772214, -14, -14, -2.7641899198954634, -2.9020369548344256, -14, -2.950976667472879, -2.7066157784953018, -2.6783888744557824, -14, -2.6887982814338285, -14, -2.668106489815909] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0879  total reward: -2317.0176361899485
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0071129056928694, -14, -14, -14, -2.82886591728865, -2.758932738094395, -14, -14, -2.8265408362638866, -2.9496970410958068, -14, -2.946263685441106, -2.7803844788345553, -2.746524419026529, -14, -2.767943384308903, -14, -2.747698594221138] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0880  total reward: -2322.599636057839
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.3315748991171894, -2.895097338424208, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0881  total reward: -2328.5556147877123
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.6895116076397936, -3.2403962472711285, -3.062302275063493, -14, -3.103050776146184, -3.097870612824171, -3.4847109902405635, -14, -3.1216426644109507, -3.224963918325579, -14, -3.2436440023248347, -3.0899997988391603, -3.008902511614884, -14, -3.069669068651288, -3.1702302342192388, -3.0608813914496706] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0882  total reward: -2334.6391600750003
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.398510405540123, -3.470927664612479, -14, -14, -3.466480152925578, -3.57318065643189, -14, -3.6876008745851796, -3.4184396760115896, -3.3975747474389286, -14, -3.404734802269306, -3.5089102356163515, -3.3940336796481416] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0883  total reward: -2340.9431934581153
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.362985458221865, -3.0718972833726426, -3.052425041409067, -14, -2.9429403222903696, -2.9676223188685253, -3.2963444965553177, -14, -2.9780105784811006, -3.069087572491307, -14, -3.206865686652051, -2.9326276833495686, -2.9500953332483606, -14, -2.9187522094877956, -2.98444571477421, -2.9099997034663114] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0884  total reward: -2346.4508205495686
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.9435296453894497, -2.7377441172965318, -2.8006415100911295, -14, -2.6690714956390273, -2.6249267158134586, -2.9372309477065963, -14, -2.6580930370678475, -2.7308644977552583, -14, -2.8433976405621264, -2.6206818919730894, -2.6616282785972882, -14, -2.603696517376627, -2.627048489554988, -2.59762738798719] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0885  total reward: -2350.9254639840956
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5970714367536116, -2.168741399074199, -1.9803418211264063, -1.9352868592169983, -2.1857311416691845, -1.9030965864303548, -1.9198217686317687, -2.110198036335727, -14, -1.9223781300161369, -1.974046484195499, -14, -2.102854765398822, -1.8922560656874199, -1.8802175999808906, -14, -1.880021564979805, -1.9231267103104859, -1.8770160465400827] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0886  total reward: -2355.1879012882746
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3022413148378136, -2.750021489916868, -2.517582221809021, -2.461241534287994, -14, -2.38287261904152, -2.4555614346916146, -2.7638970465788675, -14, -2.4439272725744052, -2.519919222218609, -14, -2.646667408478692, -2.402862005941769, -2.4020986350454345, -14, -2.3926115525519283, -2.439237400794753, -2.3854212576388774] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0887  total reward: -2359.950367745264
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3394644120652957, -2.71163873765584, -2.5150152582178897, -2.488469965991025, -14, -2.3517729628668946, -2.382137951100387, -2.624566844450499, -14, -2.4284376484209407, -2.471491548950743, -14, -14, -2.3795726360655376, -2.465584872987399, -14, -2.3842572850435237, -2.3910629903340976, -2.3795938379476183] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0888  total reward: -2364.157185325329
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6073917568214555, -2.105358110962326, -1.9550091381897177, -1.9463441784050504, -2.1464138536555883, -1.889447545932026, -1.8927258081425131, -2.1054837203241847, -14, -1.8939032987594215, -1.9459076988629018, -14, -2.0796929268922133, -1.870196886218255, -1.8663933606666359, -14, -1.8596630744554108, -1.8912300484675464, -1.8550446171983768] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0889  total reward: -2367.8599364414563
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1902288048291605, -1.893698376554055, -1.9514237557410854, -1.9244920206327911, -14, -1.895251920321571, -1.8701011891579777, -1.9281149593470444, -14, -1.8868081670612626, -1.9416144688757733, -14, -2.014300523925504, -1.8582465948498865, -1.8319741675001882, -14, -1.851986465547572, -1.9234217614987956, -1.8477064989287253] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0890  total reward: -2371.5600301904133
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.864764878634179, -2.0411783215478767, -1.9713822949763808, -2.139503885604233, -2.274318058770165, -1.9311561913532862, -1.874041032085339, -14, -14, -1.9132529309772537, -1.9798267818484798, -14, -2.007259330326964, -1.8944707979440865, -1.8848862297250197, -14, -1.8784223328881553, -14, -1.868119581456785] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0891  total reward: -2374.528252096992
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.818878648475194, -2.0325358955075465, -1.4852995981536856, -1.255235086755342, -1.1521270810781148, -1.1292049789495056, -1.265534382402654, -1.135992466033724, -1.1077284972137378, -14, -14, -1.1388823509262047, -1.199879111875713, -14, -1.2007545505963053, -1.113745897018762, -1.097886658139434, -14, -1.1102001087867746, -14, -1.1001023251225324] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0892  total reward: -2376.6686497375176
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8223657103307722, -1.8292403216079707, -1.4569826058278184, -1.1850381790485656, -1.1042848857984555, -1.0890818152687487, -1.2279160569320056, -1.0366082429474281, -1.0729523414807032, -1.1702865045409594, -14, -1.0688857665391491, -1.1050686888264971, -14, -1.1396585535830326, -1.0489319894092028, -1.0438409447793333, -14, -1.0461898673401568, -1.0770626340184577, -1.0425109823855079] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0893  total reward: -2379.12286806789
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0259948850407885, -1.6668266340213316, -1.5002475569705331, -1.4672906316493401, -1.6951181366810673, -1.4170344541851005, -1.431925612157871, -1.564398937144257, -14, -1.4455998901135843, -1.4729557757480936, -14, -14, -1.4172840486541909, -1.4595910450165914, -14, -1.4212688868220495, -1.443573329989713, -1.4176100874252267] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0894  total reward: -2382.6579552048247
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0663423955846696, -2.3570100390264135, -2.2449445715804197, -2.2900330430486115, -14, -2.1281677055689743, -2.1559229666106274, -2.360107859642849, -14, -2.1610582428502507, -2.2170323386546986, -14, -2.281377685044699, -2.1334636296846994, -2.1144734920662622, -14, -2.1224982691564365, -2.1568054281127966, -2.1180526827494925] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0895  total reward: -2387.1068972429293
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3313356907299227, -2.640928451813004, -2.44207956578182, -2.470101916864792, -2.6704685592491413, -2.4055414654967335, -2.348907282354839, -14, -14, -2.420414294484271, -2.553508764258725, -14, -2.5307218930926783, -2.3614184111364316, -2.3281069720544596, -14, -2.356153081688391, -14, -2.334468546038128] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0896  total reward: -2392.237317184961
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2332909609491316, -14, -2.9022095430597523, -14, -2.7895126480723476, -2.8735788100685444, -3.1366390371890533, -14, -2.8655328789932377, -2.9559145669416123, -14, -3.0292223382299395, -2.8186556346120835, -2.7989199538585563, -14, -2.8111777265519176, -2.9011101652047775, -2.8023129699771654] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0897  total reward: -2398.337382851524
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2906011116845377, -3.317614246349717, -3.6009500141265933, -14, -3.372966911398654, -3.428887435309892, -14, -14, -3.311271608184286, -3.4054828164855024, -14, -3.316160611893457, -3.358211567808068, -3.3105530184907925] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0898  total reward: -2404.3584706901875
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7230697737312366, -3.1211094790267837, -2.881505012611804, -2.8149299345541765, -14, -2.782722175127217, -2.786628969933051, -3.0593286027925073, -14, -2.7956348806275884, -2.884919005148332, -14, -3.0653597496938847, -2.7526763335333024, -2.761954529068272, -14, -2.739235468617433, -2.812387147210166, -2.7304867269792683] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0899  total reward: -2410.059255105587
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.397997259300308, -14, -3.0833272643957357, -14, -2.983706131700426, -3.0534787647669703, -3.4979996972667773, -14, -3.042950352716696, -3.135362037344698, -14, -3.3308704045126687, -2.9942589260159704, -3.0187402994048735, -14, -2.979160551573128, -3.025374093650391, -2.9702976884198122] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0900  total reward: -2416.15414653018
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.1346022682954406, -3.198380456055816, -3.5350638327504864, -14, -3.191570897242113, -3.286447652697176, -14, -3.429783974612696, -3.147112754314986, -3.1364234052786, -14, -3.13444396222663, -3.196077822886968, -3.12459373617317] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0901  total reward: -2422.1833458202696
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -3.062588952225018, -3.046279526726279, -14, -2.920466921850817, -2.966931011493649, -3.3490666057835843, -14, -2.9644462890169967, -3.050058176415973, -14, -3.181082150227749, -2.9277836394616292, -2.940580329053708, -14, -2.9137327346520827, -2.965223846760793, -2.9046055539166646] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0902  total reward: -2427.725344666719
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0538578834054384, -2.7957691178848987, -2.7729468623727027, -14, -2.6653353877370676, -2.683462129112413, -2.926939320762035, -14, -2.7006100615874895, -2.7799771351441414, -14, -2.869971576208366, -2.6572665505088424, -2.643493847395871, -14, -2.643438436822551, -2.705062665220502, -2.6373932925332153] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0903  total reward: -2432.7606129021324
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4619859692107604, -2.7876717296703384, -2.540019149693801, -2.5078885819204553, -14, -2.3919147046258797, -2.4574849588075005, -2.6864826545327283, -14, -2.4578528008017564, -2.5358369643777388, -14, -2.602720072218609, -2.4138498558999526, -2.4132861077145797, -14, -2.404686507724383, -2.4907275031622116, -2.3978749428795085] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0904  total reward: -2438.7266515941474
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -3.6388562871946273, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0905  total reward: -2445.2941162015427
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.58582208315368, -3.124839691591875, -2.9372413964619137, -14, -2.877696920590546, -2.9093591546723387, -3.189142845367058, -14, -2.9898598721811607, -3.0687383761417815, -14, -14, -2.9438259160381226, -2.9416246052446464, -14, -2.9360944981626975, -2.982554700447148, -2.9286083202007216] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 0906  total reward: -2451.5428967302028
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0907  total reward: -2465.5428967302028
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.8060955160137224, -3.2712457353478017, -2.6851900766795036, -14, -14, -14, -2.896480187593566, -14, -14, -14, -14, -14, -3.036554301719957, -2.8143441317556, -2.859351275251041, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0908  total reward: -2471.0100147204075
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.188508260680596, -14, -2.896252912964782, -14, -2.756977664649122, -2.858079169204525, -3.097595562790578, -2.9119504250335355, -2.8435560615555486, -2.9114361609093513, -14, -3.0588395680346627, -2.7613725251600467, -2.8094139560180977, -2.8442467490390073, -2.7916197316121836, -2.846227330879349, -2.781927913525418] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0909  total reward: -2475.9350276420228
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.091992133387294, -2.5464999902779564, -2.306840755791163, -2.2439981880401567, -14, -2.168648380392686, -2.1712689316666536, -2.281134217749603, -2.2462081425078186, -2.215486493812999, -2.246780277233036, -14, -14, -2.1654671029401333, -2.1937015827723747, -2.204700555601449, -2.172039453664453, -2.199162955573615, -2.168035256966242] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0910  total reward: -2480.7884274331964
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.059303180233602, -14, -2.8476791342118335, -14, -2.6557041860380237, -2.67984449969723, -2.9137620837239933, -14, -2.7275418599945347, -2.7725695713984426, -14, -14, -2.6913114118788055, -2.7523285110238227, -14, -2.692902059299111, -2.718681586920131, -2.687932688232909] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0911  total reward: -2485.950678056517
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.676242946023043, -2.517017859440607, -14, -2.4976532804532137, -2.6451443405735606, -2.890885740266386, -14, -2.5697383329380235, -2.6708755841514304, -14, -2.4976532804532137, -2.5105252898484705, -2.487939104343449, -14, -2.520122874633994, -2.655098421200683, -2.5065464372830633] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0912  total reward: -2490.6168801683607
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0713347211196727, -2.4922538710650683, -2.303783914199148, -2.2746198422940553, -14, -2.2070022622499867, -2.2018837086130976, -14, -14, -2.2482438008317676, -2.353107193527809, -14, -2.3271771556861984, -2.209617895429936, -2.1925565036596297, -14, -2.1947682894069485, -14, -2.1782630075001497] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0913  total reward: -2494.327726376021
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1002018744726256, -1.7285358854812207, -1.6131986646270413, -1.592883805840416, -1.8005874253575733, -1.573334377595341, -1.543995108943941, -14, -14, -1.579484866412034, -1.6473497646616524, -14, -1.6591123985297906, -1.5531686613382403, -1.5377050332457285, -14, -1.5428671740711244, -14, -1.5325832001598652] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0914  total reward: -2497.2910975340556
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0171397710792385, -1.5937674270330373, -1.4979415782266203, -1.5212304092354616, -1.633054257321667, -1.4743826470861792, -1.441428906541823, -14, -14, -1.4804652496853201, -1.557571421141967, -14, -1.559278808165552, -1.4479834130132643, -1.429284034435965, -14, -1.4433802804041425, -14, -1.430787957875097] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0915  total reward: -2499.9674979574274
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7432944109604125, -1.4489677663507317, -1.326461340917017, -1.2865104207423974, -1.4956152170097248, -1.252436545796624, -1.270591442145496, -1.3991071931820849, -14, -1.2717684590966325, -1.3065133146350603, -14, -1.3447188053135406, -1.2561744657357556, -1.2438958123256656, -14, -1.2501199181172826, -1.2776367382672236, -1.247116388935673] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0916  total reward: -2502.484084253215
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8474999610140983, -1.4435938438639921, -1.336880548477681, -1.35662185367421, -1.4908045529391425, -1.3070730234256132, -1.2824761245380478, -14, -14, -1.3118631968447696, -1.370875975946302, -14, -1.3801228238421246, -1.2896285152259044, -1.277443981665867, -14, -1.2820318250256526, -14, -1.2726904834618666] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0917  total reward: -2504.9868099099212
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.646528990711648, -1.3622512749847255, -1.2766929374013516, -1.2774153649144795, -1.334389352466476, -1.265642103143729, -1.2380545181337608, -14, -14, -1.2844024681605872, -1.3594192807242582, -14, -1.3319638600983477, -1.2372180459812585, -1.2080965314426024, -14, -1.2408070533993947, -14, -1.230035173244085] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0918  total reward: -2507.845496976596
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.312036442517017, -1.873216092022354, -1.7504660177729636, -1.7284444332683404, -1.9598854616067447, -1.6702999683811037, -1.6784781177055386, -1.830197977335812, -14, -1.6917048344283916, -1.739754320599931, -14, -1.7977579986543808, -1.6638610827936342, -1.655327264489354, -14, -1.6537115030693288, -1.6889694735315934, -1.650590535232926] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0919  total reward: -2511.7637963903726
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2712123704623197, -2.6299290990229496, -2.408059021437778, -2.3753987084395596, -14, -2.295673570912578, -2.3055132584773035, -2.470595619330685, -14, -2.3156266256813924, -2.380767363275674, -14, -2.4648004777379056, -2.283865395095944, -2.2550591837640503, -14, -2.272851711825728, -2.3323621036445084, -2.26770887854344] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0920  total reward: -2516.5209306567003
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.388830448845919, -2.8447266492505414, -2.6238706862582437, -2.5765468547515704, -14, -2.5839387043440407, -2.5178684103230022, -14, -14, -2.5974849250454612, -2.746216784274238, -14, -2.724205956627178, -2.533556264894794, -2.4984068104995827, -14, -2.5264729912711705, -14, -2.5020750825635933] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0921  total reward: -2522.553859851296
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.5217460068771125, -3.6318157061722967, -14, -14, -3.600833469847705, -3.6981630860314367, -14, -3.861236618829424, -3.5591347170079497, -3.528469800332786, -14, -3.5436747524311984, -3.6404028811363376, -3.534522384095447] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0922  total reward: -2529.9451561734677
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0923  total reward: -2543.9451561734677
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -4.613399528042755, -3.801401274117364, -3.1436606306280077, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0924  total reward: -2550.5167913613504
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.475739876011423, -3.469205951465015, -3.588863044321337, -3.6037793075277498, -3.5045666561555233, -3.5796708003686066, -14, -3.69354370512361, -3.404463150673226, -3.43821917906386, -3.515986199006994, -3.4356891802237435, -3.514707373416225, -3.427974557254657] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0925  total reward: -2557.158885123248
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0926  total reward: -2571.158885123248
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8238929457768287, -3.2400714958611627, -2.648718433340118, -14, -14, -2.764135179434999, -2.8744939767964715, -3.1757503961254474, -2.9632490896934596, -2.8730871609733866, -2.9537280148111256, -14, -3.002661269266987, -2.7833144370490785, -2.8086814102068365, -2.892269543009474, -2.8151601210049426, -2.8842516473933157, -2.804485790309602] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0927  total reward: -2576.394880626596
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7248101868182837, -2.9611142424831587, -2.743150600614063, -2.729989453993974, -14, -2.5891329677174224, -2.6373945879042475, -2.808204025843802, -2.7064214961912803, -2.6438671643295315, -2.6976567790499413, -14, -2.8136123317105564, -2.5691785246338563, -2.595322001053034, -2.6445100268322235, -2.59273251719673, -2.6389889998158726, -2.5872770700081733] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0928  total reward: -2581.1622409703086
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.130115422769946, -2.5110679705030177, -2.3212313698124785, -2.3081720164646016, -2.5451784554985664, -2.182077012043623, -2.266552075203546, -2.5444312436032726, -14, -2.247550153259197, -2.308035399275772, -14, -2.408470292446799, -2.2127545223034177, -2.2011324705260016, -14, -2.202886461997973, -2.2460860166511796, -2.1981818190782327] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0929  total reward: -2585.635456026358
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2848043747887803, -2.6509932248625536, -2.429383729347088, -2.399053642607228, -14, -2.2553776572655475, -2.2856554211067315, -2.4117756062794267, -14, -2.335135542728305, -2.3818654911523036, -14, -14, -2.293685601074837, -2.3368015623928104, -14, -2.296447587770175, -2.328169603673778, -2.2911380440058204] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0930  total reward: -2590.5837625602494
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7954637999418117, -3.030065972727002, -2.8398594852939074, -2.8453231976758584, -14, -2.715079047236346, -2.757411942050886, -3.068788276097843, -14, -2.754306829724553, -2.829976462687838, -14, -2.996144606753704, -2.7135486091632246, -2.7092703505468094, -14, -2.698820281818992, -2.752496065221206, -2.6929288766256994] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0931  total reward: -2596.859639709605
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.612683414033394, -14, -3.5911151035893147, -3.688063537342967, -5.5678503147357965, -14, -3.6216243334046134, -3.6415004696337343, -14, -4.051278776865414, -3.5832581678816653, -3.901152968110381, -14, -3.58174719386157, -3.5801200079116042, -3.582948272729757] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0932  total reward: -2602.7237871214684
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.086637243363711, -2.672524244560267, -2.4255544744275803, -2.323829271413766, -14, -2.2534521583590355, -2.419190618197172, -14, -14, -2.3205637465150657, -2.352157563153947, -14, -2.586629157422613, -2.296007936861799, -14, -14, -2.2861275261710627, -2.2294182577842934, -2.284027403951791] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 0933  total reward: -2607.0421485431125
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8770207134078296, -2.396168025673345, -2.2133607170243677, -2.157264098002702, -2.468258122109353, -2.08479294868739, -2.1465632656737132, -2.349142927537418, -14, -2.142503332262068, -2.208707831149722, -14, -2.2934391490525816, -2.10415643786856, -2.0873167451109396, -14, -2.0940699833804595, -2.1523862722166287, -2.088943163860063] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0934  total reward: -2611.753726956573
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0530999146120004, -2.7815147242361378, -2.71718763070599, -14, -2.646427993845077, -2.6906792425931796, -2.9281565021378233, -14, -2.683498368103389, -2.7447817471740525, -14, -14, -2.6274236292716746, -2.7163745204926713, -14, -2.6374044092791755, -2.696223071374762, -2.626785464773021] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0935  total reward: -2616.7122007817834
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.325416375865012, -2.7015852106979867, -2.4692371671159696, -2.430235632712368, -14, -2.353581183997805, -2.3964552682466658, -2.5717192050171107, -14, -2.3833150050162373, -2.4311004484849166, -14, -14, -2.3321970778270154, -2.3831964263663923, -14, -2.3387305262920806, -2.391638661142404, -2.331688360437199] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0936  total reward: -2621.736705785701
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.013117982715892, -2.8515876504122395, -14, -14, -2.6238805939565024, -2.691054699732608, -2.821999307816189, -14, -2.725197969949625, -2.7586750641637727, -14, -14, -2.6989262521159727, -2.7394329553906793, -14, -2.694770688550685, -2.7122355088394303, -2.6928166434807594] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0937  total reward: -2627.1311068112136
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.739486487037581, -2.849560548617597, -2.8558190219202597, -14, -2.8250210737082915, -2.9301058702016505, -14, -2.7394864870375804, -2.750566889408939, -2.747514695358272, -14, -2.7847981079924065, -3.0042024060429235, -2.7705204315556187] argmax 14
Action chosen: switching off line 14
  Simulating cascading failure
  ok
timestep 0938  total reward: -2631.407909300081
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1326471410932264, -1.7535560627419902, -1.601509387136918, -1.5974792434971117, -1.7131978942181723, -14, -2.0943366384319533, -1.7579085050649559, -14, -1.5862652863234339, -1.6255596891508985, -14, -1.407231804341973, -1.5407045231583572, -1.5301572495075892, -14, -1.5500512874963366, -1.6349736767942784, -1.5373160018298913] argmax 14
Action chosen: switching off line 14
  Simulating cascading failure
  ok
timestep 0939  total reward: -2633.868805180569
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7973770156293019, -1.7951219416855992, -1.5345851366801646, -1.195055556015392, -1.1143652320288855, -1.1264416280308565, -1.2395171399577272, -1.0728581417086853, -1.069606039126589, -1.1720711388061802, -14, -1.074816137791364, -1.1019432229638781, -14, -1.153303619745625, -1.0623458285502942, -1.057309263832555, -14, -1.0556044975004348, -1.0780898820345044, -1.053664076146148] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0940  total reward: -2636.0298854259827
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.902245022281321, -1.926011111183016, -1.5386644447992066, -1.2703196578980984, -1.172833901408131, -1.1480955341411598, -1.3086129119379541, -1.110702308024341, -1.13594493392583, -1.2507565953514939, -14, -1.134679867935586, -1.1690155422892508, -14, -1.2228268729251242, -1.1147459809001503, -1.1099278842582154, -14, -1.1100609012228517, -1.1437788872602528, -1.1074161692675908] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0941  total reward: -2638.6316488723337
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.727431604495459, -1.5337969219587915, -1.5810207451036071, -1.5311256916315317, -14, -1.5077954411360852, -1.5215839130243678, -1.6062674248788837, -14, -1.5246710362558666, -1.5718704827325434, -14, -1.6229958540052616, -1.50360608053615, -1.485105585589081, -14, -1.4993100398860044, -1.5472057450821572, -1.4943472770835504] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0942  total reward: -2641.7085544030915
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2171794826322335, -1.8083129617283367, -1.6704027624505495, -1.6606711734788968, -1.8574302369938036, -1.6433594838626124, -1.6042476407157684, -14, -14, -1.649623266124013, -1.7320637567364892, -14, -1.7431539685147146, -1.6134096222192853, -1.5952386487390002, -14, -1.6040887249674376, -14, -1.5917999451688298] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0943  total reward: -2645.509407099422
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.025761806470793, -2.5262663802015184, -2.302728948618051, -2.275439504127423, -2.4710822778965467, -2.236192876885974, -2.240078032250233, -14, -14, -2.289245244438651, -2.4080610584993045, -14, -2.3801326120196853, -2.2296265207428587, -2.194445213998087, -14, -2.2275290292888554, -14, -2.2090527511612024] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0944  total reward: -2649.9854382948893
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1897077644837855, -2.569812439698475, -2.4000152913582875, -2.400460587799991, -2.6203275885900017, -2.316154852391407, -2.336514443964019, -2.5678434287612055, -14, -2.338973714233122, -2.41191998792158, -14, -2.5802939898588666, -2.2989053399978054, -2.308103041929816, -14, -2.288196669871254, -2.3442619966779787, -2.2815859814693153] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0945  total reward: -2654.8265785655476
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.491837760800568, -2.976722730760479, -2.6985613802679547, -2.614828696017003, -14, -2.5689969385161917, -2.6248083485915297, -3.0392379934845803, -14, -2.621839864728171, -2.692801626228932, -14, -2.836363082426675, -2.5807567755673424, -2.5996813741554994, -14, -2.5645945943606554, -2.6001077731832676, -2.559554289189285] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0946  total reward: -2660.031694286207
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.1320491933220067, -2.7979641713100474, -2.7013066439728792, -14, -2.652077787107164, -2.712627824183738, -3.012424128003345, -14, -2.708153159946831, -2.7877150506455446, -14, -2.914164772375597, -2.664654239968259, -2.662694546110606, -14, -2.6518361381143807, -2.733729317509724, -2.6455614314696914] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0947  total reward: -2665.4986960308606
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2319788586554945, -2.9808155513110486, -2.9550866595448406, -14, -2.8800811950134055, -2.8700891822688686, -3.1363374941889743, -14, -2.878319107286922, -2.9556969677868308, -14, -3.1314515625203865, -2.8445913868399324, -2.825636420353967, -14, -2.8279256667485995, -2.887422370200047, -2.8214403131839174] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0948  total reward: -2671.2945825455454
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.404587532079153, -14, -3.0858455356804724, -14, -2.97005990802007, -3.062570675682198, -3.432613745082196, -14, -3.041684076720991, -3.131875364827322, -14, -3.298109022248897, -2.9961545792579347, -2.992550139176247, -14, -2.982972861948141, -3.054765609533899, -2.974446201501221] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0949  total reward: -2677.271724691584
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.1565115118610088, -14, -2.980531887599591, -3.0087823900981725, -3.2918096121662925, -14, -3.0631308164477624, -3.113034431139517, -14, -14, -3.0078306736103855, -3.1053964794473248, -14, -3.011834268168193, -3.0430468452966712, -3.0070822380182043] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0950  total reward: -2682.870236976269
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.6254501045044747, -3.02197048799936, -2.771341374087235, -2.699360144504199, -14, -2.6235850525901383, -2.680591434170924, -3.0067335649468463, -14, -2.6741557129254407, -2.7451487829807317, -14, -2.8672378986735256, -2.6373436688123513, -2.6339400176272405, -14, -2.6233004720320823, -2.688433777353086, -2.617980397085824] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0951  total reward: -2687.7566982575295
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2171560825964773, -2.6458292345178256, -2.406501218591163, -2.350111820023053, -14, -2.2842781492027013, -2.313681652471626, -2.5239184379877004, -14, -2.3154940570487414, -2.3812597702589517, -14, -2.4710002994346736, -2.2857655855796684, -2.267503063137142, -14, -2.274160880147357, -2.3423364955479165, -2.2684808841745365] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0952  total reward: -2691.991018257986
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.824427557657494, -2.2335471638327804, -2.0494099398626946, -2.082747130464, -2.2173435492076154, -2.0283759591222794, -1.98367023587544, -14, -14, -2.0401575626370683, -2.153542603797071, -14, -2.1562843635292555, -1.9886131388670343, -1.9588732020584934, -14, -1.9852584888200762, -14, -1.9668169373190978] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0953  total reward: -2696.087204915282
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.972977948332593, -2.4397217520170376, -2.251031520524534, -2.221565315358146, -2.4513131674063664, -2.1727719653632422, -2.1752505600242427, -2.455560168909482, -14, -2.185295343743723, -2.2428314179004665, -14, -2.3668069304944823, -2.1547229624243043, -2.1782246111741226, -14, -2.1418916881212433, -2.170771365369525, -2.1373134552376483] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0954  total reward: -2701.4226476172857
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.180261070991269, -3.276493544981594, -14, -14, -3.261067774944846, -14, -14, -3.436506343317311, -14, -3.187089105967032, -14, -3.2060580775159475, -14, -3.1981292467662694] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0955  total reward: -2709.721414396842
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 0956  total reward: -2723.721414396842
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.705952992144674, -2.9920882387815735, -2.496460397553925, -14, -14, -2.6855557705760313, -2.67520969196772, -2.8647129195443513, -2.764194958500874, -2.696937619259927, -2.7637953963139377, -14, -2.845854802196002, -2.624415676432679, -2.6422356315076243, -2.707232883425112, -2.65207306788873, -2.698625588235829, -2.643059249408572] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0957  total reward: -2728.3680635293977
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1192509781241213, -2.4261841159347437, -2.27637322081457, -2.3022084654941626, -2.491645917732787, -2.1612749089566243, -2.1871290315236727, -2.3192201252778526, -2.246036473728688, -2.1985936303413176, -2.247540048549774, -14, -2.33811111537371, -2.1353918753761354, -2.1731547595501643, -2.1907990741375603, -2.1560043923076826, -2.2052884902959717, -2.150188735001629] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 0958  total reward: -2732.8910935085983
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.5575633813150978, -2.3998178834547406, -14, -2.3763719114028197, -2.535218015548134, -2.661328931281274, -14, -2.4594496920891484, -2.563819449439917, -14, -2.37637191140282, -2.382003155616077, -2.363732498438826, -14, -2.3995495659557475, -2.591121149774958, -2.3876381038245267] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0959  total reward: -2737.0411119048167
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4226255685215414, -2.0301748213291027, -1.8571248813072618, -1.8400122454041024, -1.983559149465987, -1.850794834973352, -1.7960104197184232, -14, -14, -1.8636386517650467, -1.980244541372103, -14, -1.9481301126965713, -1.801297173418276, -1.7641404986520697, -14, -1.8047565806039314, -14, -1.7862858977797376] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0960  total reward: -2739.8287542507114
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6216442434911542, -1.8112151904602014, -1.4575049176412846, -1.2029174000829657, -1.0749076506778947, -1.0574759112104903, -1.1689834020193024, -1.0197310076728978, -1.0574437901661566, -1.190128863527224, -14, -1.0496568427001705, -1.0809183868544447, -14, -1.1433512391851024, -1.0309687280613544, -1.0316876736063727, -14, -1.026112492972752, -1.047158899241252, -1.0235018472430024] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0961  total reward: -2742.273798212627
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4046573733945673, -1.405497854948902, -2.0576906821425203, -1.5303677966061755, -1.4373513088928491, -1.6041764298115035, -1.4828358348049984, -1.0878741603104911, -1.8922438431624145, -1.6853385639044007, -14, -1.4406070107845004, -1.4616829205147746, -14, -14, -1.4451609686340694, -1.4209971863197537, -14, -1.4253852002708967, -1.4126416855816701, -1.4253129542422913] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0962  total reward: -2744.2158339665957
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4837173663842098, -1.5434116182893505, -1.158734846004209, -0.9759807896193464, -0.9030244323494665, -0.8778101286001402, -0.9919923450537289, -0.852740900402707, -0.8766276858463777, -0.9921491530907591, -14, -0.8756128332371778, -0.9047824595531891, -14, -0.935964932085766, -0.860758331439747, -0.864479154554638, -14, -0.8574206822037522, -0.8689509640647883, -0.8541615936582331] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0963  total reward: -2745.714467616738
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0735240409532945, -1.1499667376376392, -0.9056790128833555, -0.7583453563114414, -0.6828949479212734, -0.6638402484840793, -0.7661868236280586, -0.6443869508487864, -0.651216675154398, -0.723078083156355, -14, -0.6615105858072914, -0.6738765423888373, -14, -14, -0.6456794735102348, -0.6780050138109743, -14, -0.6471947449411078, -0.65488067198425, -0.6458927497401021] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0964  total reward: -2747.132666406242
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3549187621161665, -1.3575816318552565, -1.0982632108034962, -0.8789402043732153, -0.8198483433824643, -0.814697436173369, -0.9117707606237024, -0.7740205173399907, -0.7917043276548622, -0.8711678050503342, -14, -0.7925712664338105, -0.8139745822507657, -14, -0.8409191586104988, -0.7793098747777037, -0.77506774771748, -14, -0.77510031684058, -0.7941671259491959, -0.7738118386552117] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0965  total reward: -2748.6668627616314
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.280559187026745, -1.3554349969848183, -1.0509099284306889, -0.8837021411298542, -0.8036693264896904, -0.7808686838024982, -0.8873940178368046, -0.7623071398236955, -0.7797288874449495, -0.8796915976292745, -14, -0.776311587020978, -0.7966678370536723, -14, -0.8384566569830498, -0.7662948369801196, -0.7650284370583128, -14, -0.7619351054378917, -0.780415548243842, -0.7603845167338058] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0966  total reward: -2750.5887685576376
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9796313351612802, -1.933562358621232, -1.6907505048086842, -1.3160581571243115, -1.2294990842053959, -1.2434221097158218, -1.3816252727625824, -1.1833405813558262, -1.1811366855913283, -1.2568399102877126, -14, -1.1879398527509764, -1.226941488256166, -14, -1.2805311592930197, -1.1699023128708137, -1.1577250165892379, -14, -1.1655559146019687, -1.1951992441684385, -1.1615212792724863] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0967  total reward: -2753.034826487927
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8456904993600305, -1.4207860717857501, -1.3437286903023415, -1.3942399166344441, -1.443470796958564, -1.3432940743452149, -1.2922037333324348, -14, -14, -1.33612622558567, -1.4052681531351585, -14, -1.4020293513126756, -1.3011055412377552, -1.2794321002863633, -14, -1.2988082024983854, -14, -1.2883329137002688] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0968  total reward: -2755.864843892365
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1879086526692815, -1.7656033531949706, -1.6425570457156908, -1.6263068428845673, -1.835995142311994, -1.5729743074516478, -1.5779525954319131, -1.7180976940088448, -14, -1.584342707379786, -1.6336805037240043, -14, -1.702262692624683, -1.562780129077294, -1.553470353545477, -14, -1.5556984961923088, -1.5888568020370637, -1.5505853041514694] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0969  total reward: -2759.15853981623
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4398792751036744, -2.0574494373300203, -1.8520697706684173, -1.7867878008693283, -2.100218350734529, -1.7670279804952365, -1.7734256020952293, -1.9082716957532349, -14, -1.786959884020753, -1.8471264147841988, -14, -1.9054427637252753, -1.7562305415856678, -1.7418837717714564, -14, -1.748587117483374, -1.7989635554420753, -1.7431106197135684] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0970  total reward: -2762.952853344739
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.937230808050465, -2.3009860107437747, -2.1550835746401242, -2.191239313872192, -2.3992781715744416, -2.1323538465645564, -2.061501179135536, -14, -14, -2.1160141364562866, -2.212961302954841, -14, -2.237495731102475, -2.0805310595283566, -2.057724192144587, -14, -2.0679716439693046, -14, -2.05242975673769] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0971  total reward: -2766.836036972139
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4918316192421632, -2.0478692176266087, -1.9077053104000918, -1.9062433798179812, -2.0418567363474565, -1.8837966752023885, -1.8473598653604708, -14, -14, -1.9085516025298177, -2.02653411075435, -14, -2.002916177287913, -1.8489712797779907, -1.8157035544262063, -14, -1.8495614881485087, -14, -1.8307538706622801] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0972  total reward: -2770.9037884838544
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1500558936585272, -2.78717722507012, -2.4201182032311497, -2.269474863448849, -14, -2.2383898440355354, -2.388254604556331, -2.451875154545872, -14, -2.31368165149733, -2.414596199718969, -14, -2.2383898440355363, -2.2390828183823577, -2.231630906979523, -14, -2.2651546431091276, -2.4438933601501454, -2.252047957289148] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0973  total reward: -2775.090873683665
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.67983430581966, -2.216302701482608, -2.0502665131637485, -2.0269260161481735, -2.2592122178143046, -2.0166004349844555, -1.96957297967077, -14, -14, -2.0247844674319007, -2.1222127634587356, -14, -2.1320632243759845, -1.980436654794627, -1.9548972547606107, -14, -1.9697418536065467, -14, -1.9554542928309826] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0974  total reward: -2779.9413620057453
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.9693923647290963, -2.912691065036909, -3.0121744591198314, -14, -2.9387119792303698, -3.0055307328118337, -14, -3.059387202702472, -2.911152493462328, -2.8646282151739717, -14, -2.9007519929423364, -2.9800975984743934, -2.895591067319904] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0975  total reward: -2784.852848015042
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2065855633765583, -2.3050716938122213, -2.1606273897879538, -2.30358942032984, -2.503495467109039, -2.1366483706983828, -2.0480796794390193, -14, -14, -2.097857603990219, -2.175837824230356, -14, -2.1957694817926336, -2.078277735717613, -2.0645105070317156, -14, -2.0593961791744277, -14, -2.046857794122664] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0976  total reward: -2788.338693420841
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0458133267087386, -1.6557633155783928, -1.5116836925124588, -1.5037204009577725, -1.6959004706829388, -1.4759050545933885, -1.4547723853827053, -14, -14, -1.4887918631830517, -1.5558460338157862, -14, -1.5760358290726688, -1.4589072077185754, -1.4464533806801885, -14, -1.4483415778580533, -14, -1.438987611676311] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0977  total reward: -2791.400284047233
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2925474420075345, -1.828534797046333, -1.6954370811316108, -1.712668123544337, -1.8425317477736078, -1.6615572363140731, -1.6411866667997506, -14, -14, -1.6786002373128244, -1.7656049382817025, -14, -1.774764951680073, -1.641172206326427, -1.6208368130872282, -14, -1.6368268767113048, -14, -1.622603014714992] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0978  total reward: -2794.8989757077397
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.763620411249829, -2.166430567789122, -1.9851383367421558, -1.9927004491679279, -2.201287135262659, -1.9038674847713826, -1.9070315875035695, -2.1216617180095816, -14, -1.916430976202602, -1.9700237926169812, -14, -2.0431508908812863, -1.8932725381453963, -1.910670173636875, -14, -1.882894056600965, -1.9309078740085552, -1.8778548474196863] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0979  total reward: -2798.50421116275
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3226357537375537, -2.015723578195011, -1.8253653954599753, -1.753508885039187, -2.0057430488878705, -1.7242447904287952, -1.7733226059104716, -2.040205680325758, -14, -1.7669568221465697, -1.8178614179379753, -14, -1.8932536569362062, -1.7409975613561741, -1.7540059922534352, -14, -1.732032568024112, -1.7641358808799015, -1.7273806075907945] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0980  total reward: -2802.139716874586
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3033749779252033, -1.9515752084946638, -2.0131428973056966, -2.023189490428988, -14, -1.8549220476180523, -1.9094515630357092, -1.9584282303320604, -14, -1.9409059067616126, -1.9710480968312827, -14, -14, -1.9153206495427142, -1.9308895447024175, -14, -1.9131815045425924, -1.9323545941832243, -1.9112609214073417] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0981  total reward: -2805.9632069313516
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.072236914373578, -2.222611788041384, -2.0912520960240255, -2.2051303589848947, -2.391811406448748, -2.007888518247403, -1.9863128543877329, -2.0804969597154352, -14, -1.999535134065218, -2.047780654510549, -14, -2.095528851571668, -1.982281696256515, -1.948625891172583, -14, -1.9726257835740517, -2.0222280854135755, -1.9685680091473443] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0982  total reward: -2809.266475910229
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9030650600038879, -1.560541837590573, -1.414456772958549, -1.4067495012694833, -1.5489246844369724, -1.3970919420399404, -1.3671774253162552, -14, -14, -1.409855189331821, -1.489893239395718, -14, -1.4892196465552645, -1.3712732279173436, -1.3529293843633603, -14, -1.3667965813638696, -14, -1.3546430877047688] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 0983  total reward: -2812.1563667402115
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.16838800687322, -1.7585479126297712, -1.624201048139612, -1.6064912968644458, -1.7964641386574263, -1.5408701889774146, -1.578108358575508, -1.73061978462771, -14, -1.577124755502061, -1.6297107988912791, -14, -1.7038252146612305, -1.5459102405951006, -1.5427595759576818, -14, -1.5419825968899468, -1.5791416466036436, -1.536961445619013] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0984  total reward: -2814.2483740988246
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5740623524698658, -0.5661408557037043, -0.7437515191705906, -0.668680156154265, -0.548061007851589, -0.5566929286957594, -0.556630356001981, -0.6963148782276127, -0.5545610556503752, -0.5611773469664773, -14, -0.5819490049392673, -0.6108139772022173, -14, -0.7457787125733221, -0.5580023504444499, -0.5690119198105951, -14, -0.558138056675878, -0.5822073031037251, -0.5550459129942477] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0985  total reward: -2815.569465969229
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1676638703637934, -1.135512898674564, -1.0360562808410712, -0.8895341152720659, -0.7311911949917284, -0.7863042106301747, -0.8736884651698413, -0.7773465036619004, -0.7895447551552996, -0.8810525555649842, -14, -0.7917460726459091, -0.8176777090744233, -14, -0.8401663808385954, -0.7796337186493212, -0.7655970815628875, -14, -0.7749807411963392, -0.8021051355428853, -0.7730308625526796] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0986  total reward: -2816.947563161856
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1136011843696496, -1.142753113609328, -0.9037685888574524, -0.737694429226091, -0.6839814444527696, -0.6742066424512142, -0.7545588392294852, -0.6437773150958873, -0.6663586644574145, -0.7401996178113788, -14, -0.6623242485514801, -0.6825302281826173, -14, -0.7114687019678025, -0.6511826533237506, -0.6481875685762741, -14, -0.6487679799279576, -0.6635657978009841, -0.6469059976352715] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0987  total reward: -2818.141160877005
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9385017094958038, -0.9452807225767469, -0.7740456954712281, -0.6209353649984312, -0.580718363543927, -0.57934268603741, -0.6488738158597327, -0.5435629639083062, -0.5503134908126788, -0.6015294735206717, -14, -0.5604007167047577, -0.5703850916091687, -14, -14, -0.5494325506546011, -0.5763777266325125, -14, -0.5509846502774584, -0.5566295420929797, -0.5498204000526296] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0988  total reward: -2819.2100284144426
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9119356460686205, -0.9163000484485713, -0.725396837567715, -0.6001831536117395, -0.556585769477325, -0.5443559348980825, -0.6215714771657064, -0.5308124361652905, -0.5358999381473838, -0.5847432951689069, -14, -0.5397869389746395, -0.5577505339524066, -14, -0.5782448859627275, -0.5291787924130433, -0.527298284303127, -14, -0.5268388985888818, -0.537154507375488, -0.5253045735294859] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0989  total reward: -2820.4448331056283
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5330909704820672, -1.1896752153532602, -0.8272530153076085, -0.7184785589088895, -0.7469497955599784, -0.7390979850598611, -0.8372063022900675, -0.7287522642029556, -0.7178671124328267, -0.7812241417376519, -14, -0.7234426401517666, -0.7410664941688674, -14, -0.7784420407105759, -0.7153730786103218, -0.7151994316163102, -14, -0.7107632498340433, -0.7236007719536793, -0.7095001176568408] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0990  total reward: -2821.9029305779413
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2624841381995515, -1.3478733511375465, -1.014136775995123, -0.8641689656079004, -0.7897357706003783, -0.7653589107976512, -0.8644232121326104, -0.7496738467945574, -0.7689067083977476, -0.8683961483313116, -14, -0.7679313121966749, -0.7931894043110032, -14, -0.8298970406132724, -0.7543781009470533, -0.7583397736769178, -14, -0.7512255711755342, -0.7627267025002067, -0.7485973546557286] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0991  total reward: -2823.173678424232
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5416960783904956, -0.5346344321176365, -0.6489719126745815, -0.6287628200524515, -0.5144710087524236, -0.5205986091767262, -0.5228620787673625, -0.6480361744214754, -0.5232320844216939, -0.5272042675861469, -14, -0.5480905563949531, -0.5786884490610998, -14, -0.7192322658462945, -0.5246740846744442, -0.5352475606732808, -14, -0.52606258090952, -0.5527216435916773, -0.5221504916353036] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0992  total reward: -2825.19185628316
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.051090388064269, -1.7189206736712659, -1.422086946932127, -1.5446466723841739, -1.6961281399576216, -1.5112831395238173, -1.532669790581814, -1.7794628350896533, -14, -1.534534170249333, -1.5817715269088242, -14, -1.6209993672388447, -1.5173730263362544, -1.4994123196676894, -14, -1.5080428912288424, -1.5472298718277349, -1.5037068501752886] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 0993  total reward: -2827.937909960629
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.828010985649512, -1.513101984810851, -1.3980885466140214, -1.3711830045676718, -1.5381919345039352, -1.3194089033735261, -1.3639008402872028, -1.5164721656251035, -14, -1.3582456355826884, -1.4038934677409411, -14, -1.4626829493133693, -1.3330530677192889, -1.346240190236414, -14, -1.328552109403999, -1.3763494867102692, -1.3239667305367802] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0994  total reward: -2830.7035587296386
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.02660614197369, -1.6868862813452616, -1.5299528287783886, -1.4910652870607985, -1.7212727100359686, -1.4546298179655153, -1.4780413789323366, -1.594567357357248, -14, -1.4787698991815654, -1.5083909006102907, -14, -14, -1.446436943561165, -1.4880040250196542, -14, -1.4503990652969907, -1.4823402065014646, -1.4462398656364273] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0995  total reward: -2833.789538990618
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.368176932801171, -1.910894314538182, -1.7401441046521173, -1.714860871915745, -1.9995591903593832, -1.6110466622917738, -1.6348010896826342, -1.742207977225652, -14, -1.6703584379131367, -1.698575819855704, -14, -14, -1.6428331557522438, -1.6702281477120238, -14, -1.6419745994626411, -1.6570584935227106, -1.6397403953424219] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0996  total reward: -2836.8889457670784
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1519655994785456, -1.7004210807803528, -1.5717614359464125, -1.576277987474678, -1.737398045798762, -1.505479197162334, -1.518529541273718, -1.655496164150561, -14, -1.5242171576399581, -1.5668430500121728, -14, -1.6425477738534031, -1.4992017032205716, -1.4967122486971896, -14, -1.4912777784596554, -1.5315695823338744, -1.4883601141690819] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 0997  total reward: -2839.674372842043
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7687532818665284, -1.537063350044816, -1.3741317412935499, -1.3154054700387352, -1.5308676572157527, -1.2970404199580932, -1.328843149255789, -1.4914338175333555, -14, -1.3303214201302895, -1.3742508426528177, -14, -1.416219699542939, -1.3071069447701356, -1.3098689706563522, -14, -1.3013141718357975, -1.3298900185943812, -1.2970669607951861] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0998  total reward: -2842.3701656729404
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.997064755550845, -1.595810323485226, -1.4797851016237649, -1.4736820901996934, -1.6649654480325886, -1.3955589238216493, -1.4105968052471585, -1.5363097428939378, -14, -1.4266958968687347, -1.4542578798342587, -14, -14, -1.3987900800085507, -1.4375399804869404, -14, -1.4025596503006017, -1.417164451740947, -1.3987524109395022] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 0999  total reward: -2845.000323911571
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6949395809256729, -1.4438215974194637, -1.306694732084456, -1.2612579765779934, -1.4506060668642686, -1.2275248224212696, -1.2729476768658559, -1.4282586600723122, -14, -1.2673187405095379, -1.307402257037667, -14, -1.3588739824669576, -1.2430607960135853, -1.2370879268857236, -14, -1.2378911432654451, -1.2637475405591112, -1.2345993148086314] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1000  total reward: -2847.3755327330778
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9447977376680405, -1.91257759331176, -1.675073397899896, -1.3154619549195135, -1.2167612873468516, -1.2201572788631765, -1.3956619865695068, -1.127009907553626, -1.1442409671659077, -1.2099957404609993, -14, -1.1695244017430373, -1.1902611098630573, -14, -14, -1.1498100864443597, -1.1697467024363994, -14, -1.149476416842065, -1.1615017938510275, -1.1476839990857775] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1001  total reward: -2849.8172536576403
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8537286152587116, -1.512489748483454, -1.394745340615649, -1.3692636394519522, -1.5640327043219677, -1.3152732108561025, -1.3465694137701232, -1.4580509556731305, -14, -1.3432532841100593, -1.3856809605591627, -14, -1.4337290013331896, -1.3236194762478117, -1.3108797228919429, -14, -1.3190930223263195, -1.359807609035792, -1.3147110170089855] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1002  total reward: -2852.5743364717923
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0701613797203198, -1.6513205534845443, -1.516430268453722, -1.5240275344971004, -1.6884526372530304, -1.497860432425752, -1.4557755023644428, -14, -14, -1.4929810467666444, -1.564878048165495, -14, -1.5845097592666355, -1.4661417960160206, -1.4498944109589067, -14, -1.4578260634831854, -14, -1.4462030912599086] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1003  total reward: -2855.3502777599683
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.784866737469084, -1.4983851266416919, -1.382133358479736, -1.3696154726206453, -1.4658712293813025, -1.3580051797803823, -1.3475154333912824, -14, -14, -1.3835631438233285, -1.4608480396371912, -14, -1.4564007517007023, -1.3409576940808237, -1.3180170784815162, -14, -1.341349975642773, -14, -1.3297381969162985] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1004  total reward: -2857.858098782572
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9704592085694057, -2.0837906688305505, -1.7133969306895531, -1.4046758914656974, -1.2600726139725502, -1.232454349810269, -1.4098413933922647, -1.198190030163693, -1.2134570808557643, -1.3317424042956825, -14, -1.2219293937673077, -1.2587317449150404, -14, -1.2977488343526749, -1.1995781670761327, -1.1932925815217057, -14, -1.1922194925945397, -1.2178590491846772, -1.1898039441222343] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1005  total reward: -2860.1014890203783
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8119053202358442, -1.814673619064379, -1.461062237823592, -1.1885009171302687, -1.1131736444569262, -1.1026248243274686, -1.23107325593207, -1.0656128445862076, -1.076461585558188, -1.1738971646691236, -14, -1.0796175908367789, -1.1142199870549625, -14, -1.1694254951935172, -1.0614832067290503, -1.0627254385889933, -14, -1.0568557290091745, -1.0861339318319951, -1.0535862936836364] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1006  total reward: -2862.3028599002673
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9649324131694714, -2.0609797986943863, -1.6039604312465596, -1.2982638124761174, -1.2096194404380756, -1.201565248516062, -1.31221363595612, -1.1490317272788535, -1.176087603715403, -1.3681898162716861, -14, -1.170989106503923, -1.1978645736584068, -14, -1.260067600201203, -1.1565653830768365, -1.1641947715333771, -14, -1.1496358746049877, -1.1630525470161464, -1.1477845862056577] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1007  total reward: -2864.533817028838
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7661267670331413, -1.9158136884990045, -1.5436657303963823, -1.2686507548329649, -1.1419734994947943, -1.1215482252306488, -1.2548432582716473, -1.0846919670456472, -1.111404676431405, -1.251492588570874, -14, -1.1117995208745666, -1.145484886679923, -14, -1.1950559768758824, -1.0914760031587742, -1.0992204189582253, -14, -1.0858240411121842, -1.110923615958027, -1.0831725423646088] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1008  total reward: -2866.9780807169345
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9009545650939197, -1.5464096504207427, -1.434574282176728, -1.421599778296531, -1.5662673097986075, -1.3676937603589219, -1.3949311059715828, -1.571351766248413, -14, -1.3938860364527266, -1.4329045559418438, -14, -1.508860636223729, -1.3716292414641715, -1.3780284645326297, -14, -1.3641649320778215, -1.3890683793961223, -1.3610911457324208] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1009  total reward: -2869.793764478187
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9990664752084384, -1.784197234373526, -1.5594297648472049, -1.4632213216678203, -1.8044318448593262, -1.4490382539651003, -1.537039135080216, -1.6354693693771318, -14, -1.496856554635128, -1.5615424765760253, -14, -1.4490382539650999, -1.453693309781658, -1.4421313292115505, -14, -1.4630142183580819, -1.5503071801264554, -1.4545926155201245] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1010  total reward: -2872.484179177423
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.815826715911289, -1.3682112593759566, -1.3041629543349378, -1.3719873276321501, -1.411643472860574, -1.3043995355435358, -1.2507630155559577, -14, -14, -1.2870911893543548, -1.3476848800915289, -14, -1.3547791640587332, -1.2615415050233254, -1.24275057064378, -14, -1.2582395032958125, -14, -1.2482833700244274] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1011  total reward: -2874.679167674104
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5966865167540023, -1.6833417317917823, -1.3292698592590477, -1.1006748812519456, -1.0055551604665436, -0.9845453358573749, -1.107861846127495, -0.9526833575556173, -0.9784622966335222, -1.0752658661095915, -14, -0.9789179546046651, -1.011482230173881, -14, -1.0534800008779919, -0.9585877495351416, -0.959361183658482, -14, -0.9550911624182766, -0.9789567532640975, -0.9522379260374227] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1012  total reward: -2876.6694922644474
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8376368024084553, -1.8302506850303764, -1.4374647752292302, -1.1725235925509592, -1.099694806884325, -1.0839561456238638, -1.2206761481337092, -1.0380818134884364, -1.0635216886829968, -1.1864875519406775, -14, -1.0615896689787634, -1.091375506755732, -14, -1.133290904619689, -1.0455737201265451, -1.0433212930745381, -14, -1.0404535495181702, -1.0656533434562456, -1.0380866643057192] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1013  total reward: -2879.0612576745743
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.910715945423673, -1.6396612822082397, -1.4456205022295299, -1.3754648120747588, -1.6752546038389984, -1.3630661961730015, -1.7038148766919938, -1.50729416358365, -14, -1.3982302052860256, -1.4454204868570815, -14, -14, -1.3494815974162808, -1.3547791960983897, -14, -1.3659789470649015, -1.4732169033324312, -1.3536835966387215] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1014  total reward: -2881.922954965383
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.125538335849623, -1.7660236541728322, -1.600669872009268, -1.5601058290762275, -1.7882740607438785, -1.5229463819368907, -1.5304520080149095, -1.6317875875309027, -1.5653225494621459, -1.5489955196447085, -1.5804675846386858, -14, -14, -1.5127653004791366, -1.5566895559640337, -1.5354091950276483, -1.518937036864963, -1.5336607464726417, -1.5122156933917899] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1015  total reward: -2885.3117865847184
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.644500236456222, -2.1695776422469604, -1.9931844407367416, -1.9477679453530945, -2.240594866216662, -1.8960987419976612, -1.900990976569499, -2.020454245054888, -1.9452175041490085, -1.9160325169603678, -1.9492862446664465, -14, -14, -1.876259444322272, -1.9150841068861422, -1.9063655775469037, -1.883026343840441, -1.9093396315330484, -1.8766159259441757] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1016  total reward: -2889.260442493065
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8025357935828787, -2.373471349911415, -2.2028885884265805, -2.1277656305199613, -14, -2.071862841100163, -2.091014854912045, -2.2255053309678474, -14, -2.1176217917940474, -2.163193754294366, -14, -14, -2.073560092978497, -2.109669600084262, -14, -2.0784396579175364, -2.121905131761632, -2.0723964640243366] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1017  total reward: -2893.737949890071
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.519370874903957, -2.6993522632505402, -2.5401714022863, -2.598454938276557, -14, -2.4286297251249733, -2.449037546983974, -2.716839505904813, -14, -2.454902891555331, -2.5135364048788666, -14, -2.622805396256094, -2.4236252029515803, -2.427735276187348, -14, -2.409440383906385, -2.4607612488989776, -2.405644555905482] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1018  total reward: -2899.322567427766
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.1997781178561464, -3.2379234502906202, -3.5061882911653033, -14, -3.242862198512691, -3.330333241723825, -14, -3.4444663287747654, -3.199995033440036, -3.173745957812239, -14, -3.186457211004339, -3.263232719159833, -3.1789729817898382] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1019  total reward: -2905.0205497187208
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5126579193836176, -2.8464954051118077, -2.632306160894029, -2.6432184620845214, -2.8407745370961632, -2.6003934709869005, -2.545133065640962, -14, -14, -2.6180959715988323, -2.7754982967016915, -14, -2.758837225439365, -2.550819887650389, -2.508395911099639, -14, -2.5519955821165117, -14, -2.5242363331423214] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1020  total reward: -2910.5750544334724
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.1486297784878703, -14, -3.076543146392439, -3.1026405629911333, -3.3152990576213175, -14, -3.113332188679911, -3.2052489805741686, -14, -3.317246197179585, -3.065311428636332, -3.0281350854098656, -14, -3.0533417112243497, -3.157359253233661, -3.04610880365217] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1021  total reward: -2917.0241154221108
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.544330520317065, -3.435394622119016, -14, -14, -3.5104866377537465, -3.639531670203357, -14, -3.709156073863516, -3.4669340102749184, -3.439020201074368, -14, -3.440389678414278, -14, -3.4209259032283574] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1022  total reward: -2922.4460910278685
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6464078440950525, -2.3063408713339557, -2.078151615978049, -2.031046495937765, -2.2335434396903846, -2.078143006844, -2.0204065767293367, -14, -14, -2.081984182478514, -2.2096566040676557, -14, -2.2306675087265857, -2.0221654536380913, -1.9863404987148388, -14, -2.0222479953060146, -14, -2.001049702529795] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1023  total reward: -2926.423040214061
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7553029930000577, -2.2804465070225577, -2.106400251514838, -2.0607120578459077, -2.331276613195057, -1.997161817742311, -2.039825964511637, -2.267827179091407, -14, -2.037366715519881, -2.094542803846282, -14, -2.193833689494245, -2.0042446674367227, -1.9928181439961863, -14, -1.9948919385631647, -2.031671502487315, -1.9906086874775772] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1024  total reward: -2930.3739641746706
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7410487738797134, -2.2307948799716586, -2.074297955645988, -2.046622338349768, -2.2958225629099718, -1.9635143669571538, -2.006276233734768, -2.24253820922431, -14, -2.007086426750474, -2.070692618318656, -14, -2.1419564120038546, -1.9753595346683877, -1.9829634553533984, -14, -1.9667706370498241, -2.0103482736450244, -1.9603152731317606] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1025  total reward: -2934.3738788335786
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8651048855045347, -2.304128016595582, -2.1580538913349008, -2.145553558064929, -2.3972631601918364, -2.0695889932533045, -2.0758834375959685, -2.2911674426089483, -14, -2.0808949745260468, -2.136678412435796, -14, -2.242315573794751, -2.0560998755652724, -2.0513649164398657, -14, -2.044270604943902, -2.0918331497060025, -2.039599385776165] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1026  total reward: -2938.525609859336
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9648252174839023, -2.4724599222510557, -2.2272263355295436, -2.1758613013225645, -2.4616110748985434, -2.107896301359594, -2.1805139016670556, -2.3642667247512548, -14, -2.1680272069437545, -2.24380917482093, -14, -2.3599065656992657, -2.1272098321055677, -2.122639774430424, -14, -2.1195847082980515, -2.209156295686104, -2.1121316399810577] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1027  total reward: -2944.21179270568
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.6111758387907322, -14, -3.6113542350802508, -3.7674304031260966, -14, -14, -3.6149354375732408, -3.617146991022645, -14, -14, -3.5309512146927333, -3.9488992104744653, -14, -3.578388903854096, -3.5892120418771545, -3.578286544984637] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1028  total reward: -2949.7185085908495
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6928944330824667, -2.3203240944742913, -2.096328383796638, -2.010847219418457, -2.358865344648905, -2.0019377733195216, -2.0146228539675137, -2.140548731916917, -2.0586429306125518, -2.0274896598172187, -2.068048665777299, -14, -14, -1.9764418210077013, -2.024931512526648, -2.01468576668209, -1.9835158944749414, -2.0139514826617484, -1.9757646704765661] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1029  total reward: -2954.565384586484
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -3.043916402617905, -14, -14, -2.7894392297759194, -2.857692134033986, -2.9307747201629897, -2.9297427691797497, -2.9130834084080215, -2.950447065060775, -14, -14, -2.861054431893622, -2.929590322051859, -2.8914167330353964, -2.877104352559083, -2.8969089679869016, -2.8711113251580795] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1030  total reward: -2959.2394248175797
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6212587021198286, -2.204898858168038, -1.9935336774042935, -1.9343241947625882, -2.1759869894319372, -1.8726879508795053, -1.9348952855998307, -2.062570775429586, -1.9873421894778456, -1.9328655796360381, -1.9858060003860576, -14, -2.0809783313546695, -1.8705560386564304, -1.9026522129971541, -1.9391599460226667, -1.892217864461615, -1.9365337336232205, -1.8846010013199805] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1031  total reward: -2963.12222788914
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.845880292430991, -2.376795350098184, -2.1346531525300114, -2.0686596107061015, -2.394225669778401, -2.005276865769996, -2.0638865309689574, -2.286494053567844, -14, -2.0612574227402276, -2.128961429559526, -14, -2.1846064054029624, -2.0269596525522258, -2.0145514050228144, -14, -2.018905379822733, -2.0681468880645784, -2.012247032903684] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1032  total reward: -2966.940743401892
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5697283544573004, -2.116136229095449, -1.9236565328891977, -1.877569460310447, -2.187118925781145, -1.8082815550515046, -1.8230634485231278, -1.9925597365999441, -14, -1.8524174683383712, -1.8923257062661056, -14, -14, -1.814555748742333, -1.8786389891569164, -14, -1.8187055874786886, -1.8431314316202092, -1.8132386469818007] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1033  total reward: -2971.172914287198
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.660838981894408, -2.562961151326871, -14, -14, -2.470643445321105, -2.4504428947394135, -2.5510412357722068, -14, -2.463157811521341, -2.5204302332144968, -14, -2.602038163462852, -2.436725323643286, -2.4016399877613916, -14, -2.428128505032641, -2.5054605864506225, -2.4238893302550197] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1034  total reward: -2974.9902154188117
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9588650355715942, -1.6219556607933314, -1.480978458451674, -1.463981162371369, -1.618938931925886, -1.448141490356414, -1.4295095010303869, -14, -14, -1.4645104431148077, -1.540214097557509, -14, -1.5360821964011868, -1.4325717022402231, -1.412005998743481, -14, -1.4280046957432624, -14, -1.4156611438519457] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1035  total reward: -2977.488915149031
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9148014572803695, -1.9059186588013932, -1.493612455511578, -1.2409956092188759, -1.1531011521917043, -1.124049788225108, -1.2928955346772772, -1.0986878641333218, -1.10718416248666, -1.2085969807251882, -14, -1.1120824241996885, -1.1446925462883197, -14, -1.1902868781836613, -1.095055043289151, -1.0846867480320463, -14, -1.0892858676572896, -1.1094266162219788, -1.0866937314757847] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1036  total reward: -2979.208682108966
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6654693404092594, -0.6546817749915358, -0.8565905396360475, -0.7517362393308881, -0.6231223086699058, -0.6420894139425807, -0.6369835933978482, -0.8135772120199589, -0.6320911903818548, -14, -14, -0.6722130925468512, -0.7292219747054463, -14, -0.8399014047934129, -0.6403139616445856, -0.6334292683270567, -14, -0.6442856335432806, -14, -0.6350802119028094] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1037  total reward: -2981.090103760634
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8362050978336144, -1.870943901752125, -1.6985576366322024, -1.4158722681695604, -1.2101473693244225, -1.3032291666828164, -1.4045963346388093, -1.29667108073452, -1.2681215517834616, -14, -14, -1.3050100707374679, -1.3763639108149845, -14, -1.3734156535759432, -1.2819104627836446, -1.2646811324172622, -14, -1.2697608148667932, -14, -1.2582993429983451] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1038  total reward: -2984.66979334328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.651522362480564, -2.4990918177326393, -14, -14, -2.4620165928244973, -2.3718294766284655, -14, -14, -2.429548089504821, -2.5150077014086616, -14, -2.531653922046322, -2.40459553842871, -2.3896610128886406, -14, -2.3822655485197783, -14, -2.369542213321605] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1039  total reward: -2989.8772438888914
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.382490936312771, -2.8398165026943833, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1040  total reward: -2996.0060018117374
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
rewards [-14, -14, -14, -2.8804743591801105, -3.4337595359307373, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -3.3671275307256265, -3.346753456699673, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1041  total reward: -3001.744730207254
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.256623046207326, -2.9899146895713034, -2.9737243768737014, -14, -2.98481684611736, -2.8704282749948766, -14, -14, -2.9660121683882745, -3.1068604546087135, -14, -3.1392296032753415, -2.8950163856099165, -2.8541911590382503, -14, -2.8772079023998214, -14, -2.85825403633664] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1042  total reward: -3008.02184489687
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -3.499456178728043, -14, -14, -14, -14, -14, -3.729190461640739, -14, -3.4194495787341213, -14, -14, -14, -14] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1043  total reward: -3014.6636968724724
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3106468748409856, -3.2509117088317474, -14, -14, -3.328700268240513, -3.5094173538432556, -14, -3.5125263781932197, -3.2573826820719445, -3.211803821138599, -14, -3.2546916258910694, -14, -3.222402396868143] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1044  total reward: -3021.143132563196
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2949522597738894, -3.3417851981176345, -3.701460574751572, -14, -3.337934882180914, -3.4285755600841394, -14, -3.6124452643999514, -3.29302066129741, -3.263495918750674, -14, -3.274443065517526, -3.342913896070249, -3.2676318695851374] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1045  total reward: -3027.3612391222814
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2976027165083557, -14, -14, -14, -3.020033226699866, -2.983646888048248, -14, -14, -3.0625864730772894, -3.2193382713046472, -14, -3.2016727238663, -2.9913420931307493, -2.9555189028730093, -14, -2.978450543525713, -14, -2.954610640334876] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1046  total reward: -3033.1550249625266
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2015419958600884, -14, -2.974093483410367, -14, -2.9068008481188743, -2.8591682725269156, -14, -14, -2.9140573009406086, -3.0290065035409057, -14, -3.053674856661916, -2.8767452663409974, -2.8478085025960063, -14, -2.8577339569990055, -14, -2.839175199910147] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1047  total reward: -3038.553870930616
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5720202437786797, -2.9185356492047627, -2.6688793158651367, -2.663066771126852, -14, -2.6064498787326156, -2.589196090020909, -14, -14, -2.652571505781904, -2.795077538631609, -14, -2.7696765820400593, -2.5856821452428704, -2.544600253802616, -14, -2.5826613158811345, -14, -2.559670768179306] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1048  total reward: -3044.1582079580985
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.113474763289614, -3.096238882901179, -3.215332695460584, -14, -3.1183292749817326, -3.2014311345923434, -14, -3.2890394993387497, -3.0769205802134505, -3.029868995506101, -14, -3.0662596115703207, -3.1543514379664295, -3.059736773679881] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1049  total reward: -3049.761272034216
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.6347690046813192, -2.9536584791156324, -2.7193472548755673, -2.6844183096211682, -14, -2.608922909071404, -2.608040555773974, -14, -14, -2.6599918250016468, -2.782585097607979, -14, -2.7776544498593743, -2.6088625885321886, -2.5930331280758905, -14, -2.5912768194674243, -14, -2.573195080611083] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1050  total reward: -3055.0902235357025
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7986001918969974, -3.070472172124718, -14, -2.896477190499704, -14, -2.802445660324388, -2.8069292696057566, -14, -14, -2.8457444588467866, -2.9829818575904916, -14, -3.0424980759580817, -2.7894398829365317, -2.7636846248029103, -14, -2.7777628235358347, -14, -2.755756420875847] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1051  total reward: -3060.959277946283
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.1889167368059987, -3.140553706044652, -14, -14, -3.2176800807815504, -3.3552145858629943, -14, -3.3736006432657586, -3.1510916384175838, -3.1127964945074456, -14, -3.131989505667367, -14, -3.1132979897039843] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1052  total reward: -3066.2420150622197
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9969101738604307, -2.461336669452493, -2.2898794582278352, -2.2586658282278886, -2.5213922548287395, -2.1575561970827564, -2.2479697417143507, -2.4403661778639067, -14, -2.2311311785534165, -2.309209800864269, -14, -2.431255940875695, -2.181193541457024, -2.175980280940968, -14, -2.1771656524831995, -2.256701126143478, -2.1699406214295207] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1053  total reward: -3071.368384897942
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.4855433214213165, -3.015532429105834, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1054  total reward: -3076.9643060413455
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.2297667869134736, -2.713804619348144, -2.6220469177940626, -14, -2.570537474829811, -2.5677055297090945, -2.9171787828245606, -14, -2.6354845329974665, -2.7013550444964443, -14, -14, -2.588590980939068, -2.5978437797354292, -14, -2.5872455236952305, -2.6468068775647895, -2.580388714297528] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1055  total reward: -3081.3177088084863
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9894301295345826, -2.483368076070984, -2.2379707436733005, -2.190752672841056, -2.4887599483807565, -2.113495797559654, -2.1422116253499954, -2.4046515757626876, -14, -2.166010324225286, -2.2009965362370574, -14, -14, -2.1219492842304275, -2.215920284539299, -14, -2.1275969587491543, -2.143077689884867, -2.1236359802271068] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1056  total reward: -3085.4399340242317
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.939282320774714, -2.2896958279748514, -2.1293377861769778, -2.144507626748543, -2.3876337656762585, -2.0285864828108866, -2.0434530386723044, -2.2155610366984257, -14, -2.051001156809611, -2.113196069738588, -14, -2.180543533835403, -2.023285346294349, -2.0103686526573346, -14, -2.0150583637655624, -2.0649071863865474, -2.008729418185715] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1057  total reward: -3089.0392379343953
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.305721494065478, -1.8464852350555216, -1.6845876680252203, -1.668066132198377, -1.8767511666770897, -1.6003631826740585, -1.622396369480909, -1.7947607948634727, -14, -1.6258795192259692, -1.6696357412339624, -14, -1.7321891027347553, -1.6019063742322204, -1.5939599442924772, -14, -1.5936882877200012, -1.6278923136719003, -1.590574491977794] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1058  total reward: -3091.907916269791
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.799673639569511, -1.4822029310805092, -1.351087300690067, -1.3242067443848329, -1.4978306394213834, -1.289472652603523, -1.3046097405790091, -1.4579274215426659, -14, -1.3108870656342642, -1.3491920700858362, -14, -1.4061306651283325, -1.2890687909136105, -1.2875185520082595, -14, -1.2808674750524816, -1.3017968107037705, -1.278103843417725] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1059  total reward: -3094.377103080435
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9526439012747885, -2.0329161613016957, -1.7310345081721155, -1.3655044135212415, -1.2554206547654745, -1.261900206490621, -1.3811676268894357, -1.2088735213881896, -1.2164952007749097, -1.3384779848226995, -14, -1.215986777600795, -1.247339048121911, -14, -1.3297188145992656, -1.1996538819923654, -1.1930894630849682, -14, -1.1933378651945958, -1.2195783107318032, -1.1910829672262402] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1060  total reward: -3096.878824724264
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.5378241659881229, -1.343263122860629, -1.383533350325512, -1.3565649071584194, -1.5860919333987225, -1.3536778507184315, -1.3236876108470743, -1.3809644345909757, -14, -1.341853732221734, -1.3861557789338559, -14, -1.4349108442135328, -1.3203166396702357, -1.3107929025600813, -14, -1.3149850821685285, -1.3491480412161319, -1.3106386766029667] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1061  total reward: -3099.7116467713295
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2091348819739625, -1.7393327073592335, -1.6213072597970748, -1.6156356391675557, -1.8572386836391515, -1.5401603580281236, -1.5430837760497162, -1.6272519130072447, -14, -1.5530188157283515, -1.6014906709669734, -14, -1.6309379067084617, -1.5315416343094745, -1.5123893207887518, -14, -1.5271709692130726, -1.5781574895878299, -1.5221833704625438] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1062  total reward: -3103.3687666475253
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.510899322623633, -2.1412865815462547, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1063  total reward: -3108.1141506699296
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.308129291308159, -2.7028279490828293, -2.6218737566673003, -14, -2.674157728880068, -2.6230283540394828, -14, -14, -2.695676069574277, -2.835142924647627, -14, -2.8186449823965516, -2.6660645444445676, -2.641684239665861, -14, -2.6264283886492192, -14, -2.6040974408578945] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1064  total reward: -3114.44219025597
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -4.032132420016642, -3.865397925208137, -4.139406193839028, -4.047209665187645, -14, -14, -4.122318418270192, -4.298063712724059, -14, -4.363731358199583, -3.893421076211413, -3.7469167156811034, -14, -4.0515902882747055, -14, -4.019910294732688] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1065  total reward: -3121.51047225226
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.317539461875155, -3.4105391150498874, -3.793795253576817, -14, -3.394258689066397, -3.494983098638873, -14, -3.644740827543138, -3.3430809850940553, -3.3106575613164546, -14, -3.3306560824267892, -3.395098523209107, -3.32136528060901] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1066  total reward: -3127.6917419611004
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.216466112567693, -14, -3.0570147456309598, -14, -2.9599750037734838, -2.8944773798721797, -14, -14, -2.9743128950567255, -3.1135757197822045, -14, -3.1430446142268575, -2.9085037527520687, -2.878570701822317, -14, -2.889980022147833, -14, -2.8706121475238415] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1067  total reward: -3133.4928032436983
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.0092791142986335, -14, -2.9905424577723023, -2.9624494392413645, -14, -14, -3.0532107850680643, -3.2322110735372864, -14, -3.177983445481884, -2.96125198584793, -2.907514696030887, -14, -2.9578042516804155, -14, -2.9304491350737587] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1068  total reward: -3139.6722707269787
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2850970614298793, -3.3542518224381412, -3.9026717145613525, -14, -3.3432534782012056, -3.422449800787368, -14, -3.6255308362128753, -3.2978755958776578, -3.3247130161760934, -14, -3.2768524916383273, -3.32079862996287, -3.2719527872499183] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1069  total reward: -3146.3270967744497
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.4218475491307365, -3.4377176314859996, -3.681068484327264, -14, -3.45386617897692, -3.5649345022160466, -14, -3.670265018216035, -3.404906291988038, -3.3796365127114423, -14, -3.3958563510537085, -3.470531500134735, -3.382873260221045] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1070  total reward: -3152.256022108815
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.6167721339438974, -2.874398648916222, -2.672701579513654, -2.6977432764920146, -14, -2.6614665238964816, -2.5601751038641654, -14, -14, -2.6390375428993256, -2.77713484478799, -14, -2.7988685231397814, -2.584187847949239, -2.552984948350038, -14, -2.571639881439783, -14, -2.5492888216536884] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1071  total reward: -3157.2962947880346
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.465040520577409, -2.835356682239417, -2.613151710397703, -2.591891956886641, -14, -2.538100917774816, -2.520262450323256, -14, -14, -2.5705157896443422, -2.69899496189315, -14, -2.700801325436002, -2.522035339005921, -2.494006336344991, -14, -2.5128309685027608, -14, -2.4909838575659546] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1072  total reward: -3162.3638706831284
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7001374070113533, -2.8796837006963094, -2.694519240087682, -2.7608891367453525, -14, -2.6608396507229677, -2.5910892904350695, -14, -14, -2.662689009940825, -2.7991033756479418, -14, -2.79680785364491, -2.607134012684256, -2.567444022606515, -14, -2.5993427808153755, -14, -2.576592037527967] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1073  total reward: -3167.2299558830587
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.17453436929137, -2.6281596111142034, -2.4316938340896748, -2.3793765726597402, -14, -2.294064301704809, -2.359828419235453, -2.629540527207832, -14, -2.348074156063309, -2.4170752777689666, -14, -2.516385259661391, -2.3151179200199863, -2.315257013718095, -14, -2.305468573324397, -2.368058588925415, -2.2986411773239226] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1074  total reward: -3172.205675306985
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8216027130032604, -3.0570247553093743, -2.8405146149685554, -2.82428538340475, -14, -2.6696008624825365, -2.6941617681435743, -2.917584879989411, -14, -2.7329392030440585, -2.77189709493922, -14, -14, -2.680787041714928, -2.728587994157076, -14, -2.6845114725754278, -2.713628196630558, -2.681655122221625] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1075  total reward: -3177.6933996352204
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.225731066885526, -14, -2.908892143497112, -14, -2.7920399617102762, -2.903854370756908, -3.2460334910214006, -14, -2.8893645899828546, -2.9760789329255855, -14, -3.059466685979355, -2.8371746332875376, -2.825140651770417, -14, -2.824940136404462, -2.894074726500053, -2.8181234657528] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1076  total reward: -3182.9440306997526
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5304859655824536, -2.8330182264679435, -2.597996887847137, -2.5820692957658373, -14, -2.4476213941421534, -2.476876942467256, -2.6779496481949208, -14, -2.5148093513406784, -2.5671526813184324, -14, -14, -2.458364790967895, -2.534316285142095, -14, -2.4653266628013832, -2.495827705255866, -2.4585911028217784] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1077  total reward: -3189.874948573027
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1078  total reward: -3203.874948573027
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3934229804398615, -2.9021159078078353, -2.380667578228429, -2.5559214300772686, -14, -2.5178990054410377, -2.568511662185511, -2.8096698911201226, -2.6598599849280586, -2.568525910567846, -2.6298221212211215, -14, -2.7587405379263243, -2.4927220126888776, -2.510409044365202, -2.5852573482301366, -2.51978186819769, -2.582694851644265, -2.5131638341210536] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1079  total reward: -3208.6115907369344
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3406978125351556, -2.7129866843855526, -2.4980785125060034, -2.4582549412517847, -14, -2.3618443268925344, -2.401780374025441, -2.5362832887382845, -2.4711230614784996, -2.405000704698413, -2.4584551194568833, -14, -2.5729892409531443, -2.3408810213297215, -2.3659340384717042, -2.4125357546576582, -2.362530580777448, -2.4179178804149113, -2.3559745856791503] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1080  total reward: -3212.844129543716
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7943983886326955, -2.1804654112019284, -2.008245817755503, -2.0137687556247643, -2.2722612895540375, -1.9232753432554497, -1.9184411683755433, -2.038535842201298, -14, -1.9335528645771105, -1.986518890414862, -14, -2.0516730384061317, -1.904809604921751, -1.8795186849807806, -14, -1.8951316013723984, -1.942324961393704, -1.8916577854516563] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1081  total reward: -3216.151456802909
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9590172960277428, -1.5996495984956483, -1.485411056053041, -1.4907163201436255, -1.581916079283814, -1.4687096895468787, -1.441745050721302, -14, -14, -1.4850157023970727, -1.5667801058738882, -14, -1.5652870181581988, -1.4407270418359168, -1.4161050239071344, -14, -1.4400304800012578, -14, -1.427808574212179] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1082  total reward: -3218.8733787381307
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8140358195767923, -1.474680509677294, -1.3780928567366062, -1.3663374853553498, -1.5145975891730912, -1.3203664515517677, -1.3348470333318454, -1.4654205744799937, -14, -1.3350218233499533, -1.3752875471946482, -14, -1.4523283172982406, -1.3156601444236247, -1.315358089090062, -14, -1.309813876399307, -1.3403958319726004, -1.3058169113146811] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1083  total reward: -3221.210982293034
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7393231419715154, -1.7670748581386797, -1.4216092296367466, -1.1819471698041408, -1.090686018207005, -1.0671951012664187, -1.2138830768287332, -1.045740867345796, -1.0548088176424244, -1.1432112695773344, -14, -1.0606418265900595, -1.09512521946369, -14, -1.1522804476770554, -1.0399568862649462, -1.0349845292515738, -14, -1.0343763046087335, -1.0618677135290844, -1.0317866435886502] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1084  total reward: -3223.393708250176
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.563802739667212, -1.3283491063387476, -1.22041118050349, -1.1784094042842408, -1.3609260169708532, -1.1480581267179635, -1.1821529466261547, -1.309387986286696, -14, -1.1787841031000021, -1.2159279388242354, -14, -1.2597548115497836, -1.1588926047829098, -1.155455910711866, -14, -1.1543226697005293, -1.1879205235944572, -1.150939313553793] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1085  total reward: -3225.7823307459093
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.087827729020856, -2.087090775512301, -1.7822776125126158, -1.4176915373669075, -1.312591215968526, -1.3107236377391354, -1.4893795020690472, -1.2271153543950089, -1.2416457050621166, -1.3351878939365973, -14, -1.266633609030493, -1.2883707186429003, -14, -14, -1.2415957907901432, -1.2751640778653046, -14, -1.2424271931481001, -1.259494964421433, -1.2405643690147152] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1086  total reward: -3227.9975874418246
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0120138375725576, -0.9966250753934697, -1.3488711714206731, -1.1635154271535293, -0.9813547686440638, -1.0028147842775315, -0.9925777869646694, -1.2371893223646593, -0.9879503512349085, -1.0170026338897862, -14, -1.026646892136575, -1.0759875228910383, -14, -1.3234007154596743, -0.9924417467123133, -0.9933749007970156, -14, -0.994076464043108, -1.0615564862959448, -0.9881413415206636] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1087  total reward: -3231.443496422541
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.461731483223177, -2.791708674396095, -2.332729116599011, -2.5784971931226615, -14, -2.450367418768671, -2.530640803348365, -2.8212267433817457, -14, -2.5303606494240642, -2.629882091393112, -14, -2.662255721980929, -2.4814363659109993, -2.4578323164830103, -14, -2.475002660651938, -2.5890856405401466, -2.4645542120723145] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1088  total reward: -3236.3494828414223
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5456207397382142, -2.9527828743518065, -2.726522586462471, -2.6575308841278176, -14, -2.577463789937805, -2.640459072376606, -2.8729304916758727, -14, -2.632055093723127, -2.718144206521609, -14, -2.8360146297921984, -2.590596041181504, -2.567888536613534, -14, -2.5823531871522447, -2.651587164363775, -2.573257302282037] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1089  total reward: -3241.704281721221
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8733013819039646, -3.0865323241462117, -2.908431823314822, -2.9553075746140607, -14, -2.916347657288771, -2.7984585372186217, -14, -14, -2.892340315722933, -3.040570210321798, -14, -3.069122675126073, -2.81860095737146, -2.7728675075025273, -14, -2.8086597170364396, -14, -2.786910343184869] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1090  total reward: -3247.7769790938587
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2998585134081244, -3.3709789140091115, -3.652708824283892, -14, -3.37250687974323, -3.479285372647633, -14, -3.5592437622511426, -3.3197407857807923, -3.293829048830323, -14, -3.3107676379927984, -3.407750155950992, -3.299829865135484] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1091  total reward: -3253.9247102603863
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.918568564217919, -14, -2.8902476230225167, -2.9024026810134855, -14, -14, -2.9563741041999667, -3.113992453243907, -14, -3.1066856934911673, -2.888894156164643, -2.8560539131111304, -14, -2.8794031852963586, -14, -2.8539021176970545] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1092  total reward: -3259.904798173966
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.2225942814015385, -14, -3.23631971220353, -3.1409544301995944, -14, -14, -3.243749477521962, -3.4319566067528493, -14, -3.3931724348647916, -3.1700369746155657, -3.127741654188239, -14, -3.157902266849753, -14, -3.1261857958825736] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1093  total reward: -3266.302428723628
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.356513102209928, -3.304339914398083, -14, -14, -3.3876213224479006, -3.5655643482079706, -14, -3.573349703736014, -3.3119998620521733, -3.2741993721222618, -14, -3.300107489571927, -14, -3.2714447537795945] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1094  total reward: -3273.281728272407
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.763519920236748, -3.5759774399771285, -3.8608455881050396, -3.711365980614989, -14, -14, -3.8063795249953576, -3.9635036420313994, -14, -3.97384603746158, -3.5872392689838466, -3.4454613220196535, -14, -3.734231652596505, -14, -3.707854794999187] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1095  total reward: -3279.211470223433
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5702632206743683, -2.820797129896415, -2.62732204246977, -2.6363752859585525, -14, -2.5286031629429537, -2.5292173801938835, -2.7190043892720386, -14, -2.5415966018802365, -2.6211300112319518, -14, -2.7491963104191695, -2.502873953775468, -2.4867116879504376, -14, -2.4916835217133277, -2.5607070186084098, -2.4842806290065957] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1096  total reward: -3283.8297056674246
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0026580406538153, -2.4116162336992044, -2.2521608684698045, -2.246308005039378, -2.480922315577719, -2.1657630956101457, -2.178308431653851, -2.400368380517792, -14, -2.180810444804245, -2.2377028934670586, -14, -2.377276779580467, -2.1499636661296737, -2.1441093842429897, -14, -2.1378101833612506, -2.1876653502013736, -2.133954814984848] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1097  total reward: -3288.7492402378193
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.8001345396161863, -14, -2.770837850026678, -2.934043086513489, -3.127787525929945, -14, -2.8604052919155323, -2.975186987661686, -14, -2.7708378500266795, -2.779613755714463, -2.759174521185079, -14, -2.7995962985444938, -2.954485646653316, -2.7855797554101214] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1098  total reward: -3294.5211923397887
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.204155499051373, -14, -3.112217786477949, -3.027504983301697, -14, -14, -3.1037075211580536, -3.240249859374003, -14, -3.2609395452624685, -3.0528197728408757, -3.018163151958175, -14, -3.034317363003651, -14, -3.0127775807842596] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1099  total reward: -3300.4094076453976
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2547588271120533, -2.9936326703911638, -2.9651481509213546, -14, -2.965462339687355, -2.9003051423123165, -14, -14, -2.994241757993468, -3.1942473455726765, -14, -3.153474577482677, -2.9053944821074995, -2.84911007026358, -14, -2.910841137655405, -14, -2.8754377248247005] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1100  total reward: -3305.407852270996
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9500524476910037, -2.447740142178931, -2.270487245089047, -2.224737667704802, -2.4997517949942303, -2.146995940197921, -2.208763316106875, -2.475624655702792, -14, -2.2035492065396256, -2.2777702437835714, -14, -2.369022073830704, -2.165865245062951, -2.1855268060962794, -14, -2.157288209278624, -2.2165830100257047, -2.1493345553344785] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1101  total reward: -3309.9654878855185
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.541121491610942, -2.8108294883885834, -2.559633655671734, -2.5392174571402415, -14, -2.3842112312985706, -2.4057708235199042, -2.608936590872271, -14, -2.4509096385514666, -2.488208861728664, -14, -14, -2.4123605405877826, -2.4576017871867695, -14, -2.4136758396424374, -2.4371693227182307, -2.4106396743247434] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1102  total reward: -3314.964976911894
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0061480597799584, -2.771580673476715, -2.76216899632352, -14, -2.6490047157562286, -2.656863388607725, -2.920707473193798, -14, -2.678138427050403, -2.754123831752863, -14, -2.8433255659897583, -2.6367562228861545, -2.62171192368957, -14, -2.6207257673027557, -2.661741579855615, -2.6152777950769024] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1103  total reward: -3320.1667601937193
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.6159042608662326, -2.9215452884045714, -2.744704361110666, -2.7151653473033734, -14, -2.6348550439542158, -2.622344985463376, -2.86393133852413, -14, -2.6470658448724005, -2.726060939930581, -14, -2.8173121390332394, -2.6078056321570857, -2.6008117544802345, -14, -2.593083710612572, -2.6449810247685854, -2.586505486748546] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1104  total reward: -3324.8588852080593
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1792223754899114, -2.3589218940868806, -2.229772074729817, -2.325288810712126, -14, -2.1532437269163305, -2.12818697904144, -2.2702458152311165, -14, -2.1478640433722194, -2.2067373881435803, -14, -2.2761829348790266, -2.122184585967784, -2.102580825651059, -14, -2.110725865516538, -2.1528869826494104, -2.105619527591932] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1105  total reward: -3328.4901088224688
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0987348423499554, -1.7433911689477257, -1.6081798254384267, -1.5808725016401468, -1.8063415161906984, -1.5658411436137105, -1.5467516110466355, -14, -14, -1.5792149370789588, -1.6606908593571363, -14, -1.6753509626366083, -1.5498522020883114, -1.5361357584932045, -14, -1.5424601598115468, -14, -1.5286427887578653] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1106  total reward: -3331.2852993980996
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7471542803149192, -1.4253686366375993, -1.3223141250376513, -1.3217171239780892, -1.4259161462268817, -1.3113977554185698, -1.2722730984939719, -14, -14, -1.3117044958083628, -1.3851752824564478, -14, -1.373771267320804, -1.2799246769881407, -1.2566937111975633, -14, -1.2791295533551046, -14, -1.2665477868731445] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1107  total reward: -3333.423215947725
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.435728684900311, -1.5800302583883803, -1.213425148429829, -1.0275239018477522, -0.9269445081851195, -0.9022044654106776, -1.008900413254264, -0.8776444334059611, -0.9104099690168218, -1.0265640573633201, -14, -0.9051862609793044, -0.9372731541092278, -14, -0.9834982043775763, -0.8876414770201799, -0.8930882192880636, -14, -0.8848873238831214, -0.9005098960426284, -0.881222838427707] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1108  total reward: -3335.2847886182035
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6598572876539077, -1.7613227443463186, -1.3740211886057423, -1.1510349632528487, -1.041415007684003, -1.0113292917477699, -1.1699135806069318, -0.9802567981172903, -0.9897161243104883, -1.1064621417224783, -14, -1.0039997829849416, -1.0194888949226382, -14, -14, -0.9838883572161364, -1.0246198314393544, -14, -0.9852900371585481, -0.9954040605584745, -0.9839282370728561] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1109  total reward: -3337.537143759248
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7927751997832666, -1.437324315263279, -1.348830042651559, -1.3399890184424157, -1.5087328799946642, -1.2966253192781583, -1.2894436581890407, -1.4066319115497792, -14, -1.298095101523994, -1.3312612627799254, -14, -1.3859571909531558, -1.2824280289264156, -1.2727472819047194, -14, -1.2744530212586593, -1.296487014309832, -1.2720983429269521] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1110  total reward: -3340.2831500654274
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.13954122722709, -1.6897499533810225, -1.5536211477688837, -1.5601242035451768, -1.7063301966072195, -1.49936587795393, -1.5002925357002848, -1.661760750775753, -14, -1.5065189975955697, -1.5494505587131118, -14, -1.6325666789250706, -1.4855445872218966, -1.4916867409219068, -14, -1.4778105716262868, -1.5057907050013175, -1.4739079632525587] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1111  total reward: -3344.126673272165
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3677198576449197, -2.6675091205806782, -2.5142167752286175, -2.5132081738296232, -14, -2.3846089186567823, -2.413266288177661, -2.6437855901953373, -14, -2.418727386750484, -2.489259932339949, -14, -2.565023962978752, -2.386909511559538, -2.371796355764102, -14, -2.3765068373380864, -2.4276826928604187, -2.3696152434848288] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1112  total reward: -3348.865996965199
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.302995579410012, -2.7636207369779995, -2.4976046061737733, -2.438462003236688, -2.747995606422632, -2.3895295454338004, -2.432516695872683, -2.7152385962912007, -14, -2.423514066083712, -2.492365095210383, -14, -2.6605711415186826, -2.3870634029779145, -2.3872408626045845, -14, -2.3752167388339114, -2.441430029664297, -2.369708449549079] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1113  total reward: -3353.705799305084
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.443030275355497, -2.916516664320918, -2.5893459030085157, -2.5255377587011383, -2.7976470596448726, -2.453752355238755, -2.5606125778311766, -2.996692574342495, -14, -2.5198304476712603, -2.5825843489363924, -14, -2.769413937269127, -2.4879060871043195, -2.4982797691225267, -14, -2.475301106115944, -2.5229607579926623, -2.4700938903360403] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1114  total reward: -3359.020219706952
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.307798491188094, -14, -2.9434447214468875, -14, -2.878057432977771, -2.9155671964197265, -3.2371569419020845, -14, -2.9263592602633928, -2.98163117396546, -14, -14, -2.8608885918660873, -2.96339114977288, -14, -2.867688528681947, -2.906983366271372, -2.860668046629525] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1115  total reward: -3365.4783205815197
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.6542609625900124, -14, -3.604194083919493, -3.7186985789598923, -5.2674891515907944, -14, -3.631350536861237, -3.6281056928566287, -14, -14, -3.5365623519960194, -4.044759264758983, -14, -3.5964690607406626, -3.614596946198408, -3.5974328279379013] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1116  total reward: -3372.285257894695
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3000859178988504, -3.308690109981892, -3.509786171953662, -3.3991103452316382, -3.3461178250838137, -3.4041243767023017, -14, -14, -3.269800095663955, -3.326573466609387, -3.3281230092577467, -3.280698096594641, -3.319286562840219, -3.2703749611795194] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1117  total reward: -3378.3408160240433
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.7821130208776106, -3.1253834474472106, -14, -2.8991026775670474, -14, -2.7350723556267384, -2.7811403597628175, -3.0404057919162537, -14, -2.8318213208327707, -2.8792698318962366, -14, -14, -2.7867303023119443, -2.89925375714386, -14, -2.7911417400513163, -2.812818669472551, -2.785758033684115] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1118  total reward: -3383.9644035390015
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.353864612253159, -14, -3.0081452770105463, -14, -2.9215500198879436, -2.9294411851909716, -3.1983072432827053, -14, -2.939929801004173, -3.0065665246254256, -14, -3.1013115804804294, -2.911062131322618, -2.869197831061662, -14, -2.892341237188013, -2.948790596803457, -2.888515159331576] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1119  total reward: -3389.561015571061
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.162767898533542, -2.740021219839424, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1120  total reward: -3394.455025566893
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.882185773948585, -2.214673566280973, -2.2367938838201074, -14, -2.2211470624370806, -2.1665675184936157, -14, -14, -2.2307258391069706, -2.3555882334041947, -14, -2.334433446725724, -2.2067719281988163, -2.1810094921833247, -14, -2.175372934439676, -14, -2.153988775992552] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1121  total reward: -3398.604562813328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.162884728521949, -2.566613103800881, -2.383640975839846, -2.3729561523930767, -14, -2.3330781725549654, -2.288945019650693, -14, -14, -2.344731495067067, -2.457089212843308, -14, -2.4849432506429046, -2.2989227466472384, -2.278212873987579, -14, -2.284443431684719, -14, -2.2673514724869626] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1122  total reward: -3403.4112129669275
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5893285308487046, -2.8365047911582173, -2.6473017486201273, -2.7018142532731746, -2.8712369936409505, -2.6506241200538585, -2.5571161854895053, -14, -14, -2.6395549829133, -2.775891308395591, -14, -2.823747070073079, -2.5695127652547027, -2.533233689156423, -14, -2.5585445611105233, -14, -2.5392986811119878] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1123  total reward: -3409.0321800637976
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.080417984293045, -3.1587553782179913, -3.465968990944009, -14, -3.1554919705828612, -3.241359465006342, -14, -3.3286870929697154, -3.108392298718824, -3.074205629057959, -14, -3.093944736116007, -3.1633354689413027, -3.087733407713799] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1124  total reward: -3414.286013481121
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9648856011521536, -2.459516249189043, -2.258430062546771, -2.2569426568986537, -2.382007096523286, -2.2624966992822277, -2.191747968926277, -14, -14, -2.284629017045626, -2.43416576355045, -14, -2.3856635340313055, -2.1937897677007143, -2.1434636254278017, -14, -2.2018902258227233, -14, -2.179627788265016] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1125  total reward: -3418.995989742257
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.5850666134289577, -14, -2.552048022619647, -2.6891708326492716, -2.89998043654237, -14, -2.6274891234780284, -2.724675189776092, -14, -2.5520480226196485, -2.567461127287015, -2.542818610286532, -14, -2.5786871909267446, -2.7000672688057836, -2.566512635708813] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1126  total reward: -3423.5342457969964
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7824603526476723, -2.275604210987305, -2.0940790379221452, -2.0779913481277488, -2.3321659639338224, -2.058331010465529, -2.009644425481933, -14, -14, -2.072362993309379, -2.191530240240705, -14, -2.1756683423533416, -2.0226875711120544, -1.9959394070729586, -14, -2.0148598288605117, -14, -1.995437444452575] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1127  total reward: -3427.6594540701826
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9277035739671122, -2.407866374450151, -2.224321566741543, -2.2127428104100266, -2.4050733006556206, -2.1912118291317326, -2.1445905742017373, -14, -14, -2.2080391709970772, -2.3306076911152993, -14, -2.3100715023163834, -2.1528613163825976, -2.1152737282586607, -14, -2.149971043653014, -14, -2.1297708287335935] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1128  total reward: -3431.091194659304
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.915173642682509, -1.5078550244845175, -1.3950787144493249, -1.3959304380382784, -1.5598035093940161, -1.3241393049130232, -1.3427200105043098, -1.4663471027596113, -14, -1.3463075642795281, -1.380839795722086, -14, -1.4316854057496509, -1.3264428436989597, -1.3111467460199475, -14, -1.3183845506827712, -1.344262089544738, -1.3164668608629606] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1129  total reward: -3433.315718998784
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4576820367769656, -1.683022831180774, -1.204588260738541, -1.0327671917995678, -0.9498698871250967, -0.9332999638242012, -1.0145693323546674, -0.9488953588336257, -0.9208633220979651, -14, -14, -0.9491539062441916, -1.0000396940901792, -14, -1.0127031915164644, -0.9223594577188611, -0.906123558496213, -14, -0.9209424385981545, -14, -0.9133775934603227] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1130  total reward: -3435.062685240797
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.439393237060015, -1.4792944305504543, -1.199354361785812, -0.9781595661077014, -0.8919509108399515, -0.8743735876161504, -0.999399610209629, -0.8436606314103909, -0.8591211028547624, -0.9403857696016256, -14, -0.8596225096851334, -0.8837580816208496, -14, -0.9149618303813619, -0.8462807581044074, -0.8413773503548098, -14, -0.8426285256043785, -0.868821890099733, -0.8408426835167052] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1131  total reward: -3436.7005940838953
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3656761469939038, -1.4030183599690398, -1.1222066204261945, -0.9164466162264251, -0.8437099453479333, -0.8296484681031924, -0.9365253105527778, -0.7936827947887577, -0.8203743529915308, -0.9047752539896061, -14, -0.8148879613231187, -0.8393312962102133, -14, -0.8750188915173505, -0.8022304416493394, -0.7955132210207713, -14, -0.7993431219368784, -0.819433548784183, -0.79706615958178] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1132  total reward: -3438.1689730210082
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1429525058518348, -1.1617758587334754, -0.9456355874630143, -0.7740325799964912, -0.7138722667538784, -0.7024150586232206, -0.8056444633415891, -0.667564207959709, -0.6753417000259365, -0.7366496511865506, -14, -0.6871029579253009, -0.698155722363531, -14, -14, -0.6744234552284676, -0.6980697295416382, -14, -0.6757599225219145, -0.6842008550386732, -0.6746961423239043] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1133  total reward: -3439.772123778137
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6287200616084598, -1.6327644065282485, -1.3401183141069417, -1.0540940297914398, -0.9893967980362915, -0.9954154970565801, -1.0923686737438152, -0.941822349665817, -0.9542564409082369, -1.0681866047086315, -14, -0.9535508405736337, -0.9788414735681582, -14, -1.0209758603853758, -0.9427416942184925, -0.9404851421713908, -14, -0.9380147191149528, -0.9532298696273946, -0.9355865491688095] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1134  total reward: -3441.7591425580295
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7891497874674114, -1.8683853925509022, -1.4379308946538754, -1.2148203423744635, -1.1119081178842463, -1.0786184569707273, -1.2300640010504504, -1.0569320129502566, -1.077018466591805, -1.213148597892612, -14, -1.0744505323076219, -1.106345403241939, -14, -1.1626596762877803, -1.0597590972765407, -1.057299783134178, -14, -1.0545574339128596, -1.0733639447528849, -1.0514322307241402] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1135  total reward: -3444.104841879588
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.849016700449651, -1.5138487997479237, -1.3684841535644705, -1.342995186083963, -1.5215700346280339, -1.3051956216797755, -1.3216326046738, -1.4616373483725285, -14, -1.3223503991591297, -1.3629760540536098, -14, -1.423212815997984, -1.3049413215616754, -1.3000175333211377, -14, -1.2984551388080194, -1.3274095313712515, -1.2942670908345548] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1136  total reward: -3447.056277512668
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.45021450996028, -1.8978984128074274, -1.7501122322589364, -1.772983048176073, -1.9388172399446368, -1.6819885547666809, -1.6851255301610157, -1.8343528712622448, -14, -1.6987946812861299, -1.740913509759418, -14, -1.8169461842849146, -1.6705023945226942, -1.6633561588990042, -14, -1.6587199814989602, -1.696121012820513, -1.6571685422451707] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1137  total reward: -3450.7045700937406
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9375636223334736, -2.261167220319627, -2.109452742466859, -2.1407638914963645, -2.35401881473308, -2.002167384307784, -2.027616182100442, -2.2054679386880536, -14, -2.033818869950138, -2.0907711838735534, -14, -2.151000725743052, -2.0053110250360717, -1.9951308187525458, -14, -1.9959377648088972, -2.0476360254377592, -1.9911240388272067] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1138  total reward: -3454.205442451317
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0671627802789216, -1.7632821724433565, -1.5865844171800252, -1.54081562359931, -1.7162755631047824, -1.5108587164827683, -1.5514288316815459, -1.801921119102425, -14, -1.5445705654443136, -1.5843155183490447, -14, -1.6747886989082157, -1.5212657976372226, -1.5386437850009917, -14, -1.5127195203139832, -1.5338807041123934, -1.5097483187487948] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1139  total reward: -3458.087279172488
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4675918879168424, -2.7152037259778234, -2.51321174656102, -2.522800743625425, -14, -2.386843127527111, -2.4193403185090396, -2.655009720642852, -14, -2.4226852011699593, -2.4897726847364754, -14, -2.581787213811813, -2.3887169754122093, -2.3702624720766488, -14, -2.377537414185224, -2.4301126673912408, -2.3720884024225755] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1140  total reward: -3464.400830037639
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -4.138844652414298, -3.9400428934440486, -14, -14, -4.005287707951314, -4.105507018805763, -14, -4.1638112606578295, -14, -14, -14, -3.960340721945636, -14, -3.943288393074248] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1141  total reward: -3470.2551368419226
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.662667435449615, -2.1669005575377596, -2.009559295242628, -2.000205292498488, -2.2351476949666105, -14, -1.8960977703192874, -14, -14, -1.9793097329624805, -2.079382682046303, -14, -14, -1.948845921313799, -1.9442291339788802, -14, -1.9304584159991849, -14, -1.9142639108398496] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1142  total reward: -3473.9376446049027
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5946711049715137, -2.0185290419015933, -1.875727317930153, -1.911372871533112, -2.0949443884716294, -1.840476419729211, -1.799843269901938, -14, -14, -1.846668473988666, -1.9427095457731633, -14, -1.9468150958591433, -1.8105255670413203, -1.7921893581598833, -14, -1.8025230284634275, -14, -1.7864099926602344] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1143  total reward: -3477.2654038408946
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.13185837552467, -1.6949143170108332, -1.6081705898163283, -1.6376961384950313, -1.7200290090247632, -1.6010018208848067, -1.547251443289191, -14, -14, -1.5960158910277928, -1.6772398066643932, -14, -1.6747035897304434, -1.556294366757171, -1.5265077395333744, -14, -1.5540181433044895, -14, -1.5413492433316065] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1144  total reward: -3480.069420685245
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7943066089906867, -1.4578607349309196, -1.348984751023178, -1.3343068505971398, -1.4842383157751373, -1.2833121705721435, -1.308882097840574, -1.451386527691173, -14, -1.3090487931341963, -1.3496143954144737, -14, -1.41256206288467, -1.2868343522789567, -1.284991039838342, -14, -1.2812840275373472, -1.3040295547737497, -1.2775091048171525] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1145  total reward: -3482.9228622483015
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.260934513340693, -1.7945213232634047, -1.6647338891498826, -1.6656404666214863, -1.8357893511917662, -1.5905636374721182, -1.6095040347218825, -1.7694892357945415, -14, -1.6112657417983625, -1.6554421325335356, -14, -1.7386209984230478, -1.586346756850448, -1.581039969838437, -14, -1.5793486776169576, -1.6124532845366584, -1.5759324582395517] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1146  total reward: -3486.4231909256896
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.607691667422442, -2.1933047584564536, -2.0415137022074603, -1.980604478523341, -2.279643216397182, -1.9271287480857093, -1.9730285613180065, -2.161675815788123, -14, -1.963051308527146, -2.0160947002220917, -14, -2.112246118535785, -1.9374621819608957, -1.915306385068156, -14, -1.928734471146181, -1.979501625212222, -1.92439621914839] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1147  total reward: -3490.1281736711617
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4138576374994534, -2.017445632093995, -1.864251550926966, -1.847889549435604, -2.0009894740251313, -1.844105054047702, -1.8084602518673112, -14, -14, -1.8547988715209054, -1.9539005439597539, -14, -1.9736083280175938, -1.8083153364149942, -1.7787476697697213, -14, -1.805531639490752, -14, -1.789676360404145] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1148  total reward: -3493.4446394593488
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.207336427463292, -1.744990075267357, -1.6247629789252973, -1.6306510074905767, -1.8004806972331244, -1.5529421072157457, -1.5701254523397712, -1.699520640184568, -14, -1.5720014281494599, -1.6216986558280728, -14, -1.696010093604856, -1.5491635661585004, -1.5436132786896997, -14, -1.5429456301917435, -1.586423016447394, -1.537718118417267] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1149  total reward: -3496.2743635106635
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8360584689300783, -1.500690186036473, -1.3637557227239716, -1.342826162159365, -1.5063137853058233, -1.2995968462332126, -1.3240815024436312, -1.4587266364289455, -14, -1.3252723644094222, -1.3653190195257934, -14, -1.4333911714708232, -1.3016111581722325, -1.2985652103568923, -14, -1.2950596707173565, -1.326867625781101, -1.292005932897496] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1150  total reward: -3498.440495436892
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8987152515256858, -0.88794081908505, -1.109355609809981, -0.9919485222975891, -0.8647403656327917, -0.8830828566434109, -0.8723724740589119, -1.1269629422215148, -0.8726213328477695, -0.8841314973111949, -14, -0.908547721737384, -0.9453490097634528, -14, -1.2149231660912962, -0.8781709511537306, -0.8991349341183639, -14, -0.8780516459142269, -0.9108517077163151, -0.8741259933307831] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1151  total reward: -3500.9369857658303
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.294104483052154, -1.8509541573552872, -1.541235135030164, -1.706467100100981, -1.8411980370959304, -1.6442202470634981, -1.657018951931793, -1.8763437016526243, -14, -1.6679566898480171, -1.7137528422615484, -14, -1.742956035733714, -1.6460256169702667, -1.6227127029875703, -14, -1.6342908526582323, -1.6772135890458577, -1.6317499633050894] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1152  total reward: -3503.9986967801283
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.392557397659605, -1.6950248768492742, -1.6151362241840048, -1.7346227823200373, -1.8448643815551373, -1.5311503328345024, -1.539455046156694, -1.6192165718602172, -14, -1.5477368302878003, -1.5921628988881025, -14, -1.607145261336198, -1.5263900384385316, -1.5069842387278447, -14, -1.5252814719129602, -1.5600608445657884, -1.5204758792684776] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1153  total reward: -3506.265431181185
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2823550941675126, -1.3967649630448375, -1.0317344663823382, -0.8526950181844761, -0.7961594479495807, -0.788713554721009, -0.8712703283216437, -0.7753466230488044, -0.769708306832876, -14, -14, -0.7871057258967973, -0.8270322987356422, -14, -0.8301900057814595, -0.7688673535754156, -0.7600574152174301, -14, -0.7658583570674364, -14, -0.7597501623285207] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1154  total reward: -3507.642435626786
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9390766621212606, -1.1402414833210957, -0.8684175712488476, -0.7151278309732914, -0.6396151932574207, -0.6389662144701354, -0.682192812247859, -0.6309465608797084, -0.62562158241517, -14, -14, -0.6409297610582501, -0.680764867418751, -14, -0.6777030933269006, -0.6231644156700487, -0.6121134850603503, -14, -0.6243017997313521, -14, -0.617254283272917] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1155  total reward: -3508.843138958966
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0126421157248273, -1.0240782635199004, -0.8196966978038694, -0.6699754752351917, -0.6226067449285184, -0.6135392272029951, -0.6904431094637168, -0.590098231035945, -0.6040985650804146, -0.6653346744893726, -14, -0.6017167408224159, -0.6187654952042626, -14, -0.650915202245532, -0.592665641165933, -0.589007242714646, -14, -0.5899478858673001, -0.6067799772731356, -0.5885898471198846] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1156  total reward: -3510.000718520769
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0079093135996897, -0.9842003962313745, -0.7950977852557573, -0.6406963661017804, -0.6030795507452502, -0.5983173552214612, -0.6739659195533128, -0.5746803179957591, -0.5798529714100586, -0.6228070778174293, -14, -0.5823573484711121, -0.5985132832394625, -14, -0.6220787087776518, -0.5727914225010672, -0.5704718107546544, -14, -0.5700240781403716, -0.590891684616849, -0.5689897146830734] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1157  total reward: -3511.240136748256
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1613626622068636, -1.1653834610389633, -0.9542200103364101, -0.7627065530447924, -0.7099174057425732, -0.7063069470671056, -0.7899856060344523, -0.6732101595982304, -0.6849543072985921, -0.7544201187666101, -14, -0.6844959731948408, -0.705510513096939, -14, -0.731399743606982, -0.6754386906472021, -0.6743161494619739, -14, -0.6727012998048035, -0.690934677180562, -0.6704285128042423] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1158  total reward: -3512.68794837305
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3522304476819613, -1.3640345784845695, -1.0711109129014347, -0.8834288459069262, -0.822771064158865, -0.8070926880784847, -0.9124991593821932, -0.7789740372748956, -0.7971594994747655, -0.8676151010461824, -14, -0.7973028745229717, -0.8220865442026477, -14, -0.8560960218586495, -0.7827703873917488, -0.7789568992781659, -14, -0.7794055820774028, -0.8008599742113456, -0.7773831119890213] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1159  total reward: -3514.983237687557
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9645694325536247, -1.7642265692124086, -1.5593709687855173, -1.5243233828341285, -1.5925935486859821, -1.5113320931243566, -1.5672568368605444, -2.3537281380727295, -14, -1.5326208258971634, -1.5402400723270955, -14, -1.6957389113923593, -1.5205584434855395, -1.6182857319360247, -14, -1.5173187509809314, -1.515687587782401, -1.5179062025182246] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1160  total reward: -3517.9142532511287
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9470184098116585, -1.6055015487123754, -1.5070475536569539, -1.4762572515038097, -1.7196750750399497, -1.4097608122396064, -1.4227816712428225, -1.5435781086065254, -14, -1.446859980367142, -1.4702370692392843, -14, -14, -1.4206580433524163, -1.4506029024926435, -14, -1.4217621485917082, -1.4392134792777755, -1.4196834704473276] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1161  total reward: -3520.1983025071477
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8950505193733477, -0.8819762263126004, -1.2233867911877185, -1.0553544998510012, -0.8688057964607041, -0.8843541200799867, -0.8826699787043637, -1.1257943126743637, -0.872213661680895, -0.9070699051196448, -14, -0.906666866783795, -0.9476719461538702, -14, -1.1377887670559057, -0.8785239300938887, -0.8769523504925009, -14, -0.8789186533547566, -0.9221057789696082, -0.87428844377964] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1162  total reward: -3521.9070001465216
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8387356136414921, -0.8346781505385268, -1.0771527185654761, -0.95818313369872, -0.8476287022086502, -0.8383810255849747, -0.8517477035818422, -1.0731507095413915, -0.8390055419216267, -0.849857118647122, -14, -0.8811218724622363, -0.9314810494088697, -14, -1.1107662617956973, -0.8435029678260756, -0.8338482572924689, -14, -0.8448347035096234, -0.8989709648981498, -0.8398918429128277] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1163  total reward: -3524.301096649777
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1077401722225435, -1.7645833328706442, -1.4857803794682805, -1.6099468773044368, -1.7809010607917122, -1.597358188438727, -1.5755637966054814, -14, -14, -1.6154338418227103, -1.7038444941070396, -14, -1.6958209949435548, -1.589300170454992, -1.5785557859494992, -14, -1.5751579594471588, -14, -1.5602482459628728] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1164  total reward: -3527.4206398879796
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2248695989869303, -1.8701420831308273, -1.6994423500838498, -1.6791767393015127, -1.8204368684450176, -1.6964574592571438, -1.6436832494577236, -14, -14, -1.68719454877373, -1.776437461474693, -14, -1.7933919674149779, -1.6499010577508268, -1.6226730177810322, -14, -1.6494405655962923, -14, -1.6337628587344624] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1165  total reward: -3531.5036220151133
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.557318226757073, -2.4550462574913308, -2.7238391033884697, -2.480827012122457, -2.620073777983863, -3.7294543856507656, -14, -2.485298286850398, -2.512775972646284, -14, -2.4808270121224574, -2.4706060344174543, -2.5081325462491963, -14, -2.4620587221417076, -2.471662101332463, -2.46030910935279] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1166  total reward: -3535.3420116046727
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.564052614558069, -1.4533864335187612, -1.3336844757325643, -1.5895201644180783, -1.3914909285782413, -1.411505205682076, -1.5499539014887107, -14, -1.4084499191403235, -1.4412907877827466, -14, -1.511296141422452, -1.3922503227597554, -1.3920107454150323, -14, -1.3861034657830167, -1.4140003660270546, -1.383343332068053] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1167  total reward: -3538.6579440163705
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2274953425369186, -1.9976420726502981, -14, -2.015979437034446, -14, -2.0279239379043523, -2.012013327799513, -2.764918296908739, -14, -1.9953238441171728, -2.0033082181631645, -14, -2.2201482982900016, -1.9901429663396086, -2.0766504449364827, -14, -1.981550900396949, -1.9774368375415994, -1.9822479359650906] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1168  total reward: -3541.891192760813
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7897399013575908, -1.4674374552674447, -1.3424230720615296, -1.304190758890646, -1.6803175534720505, -1.2430390135454348, -1.313157927974145, -14, -14, -1.2758732309623981, -1.2882521280899608, -14, -1.3851680363681496, -1.2602345810014077, -14, -14, -1.2559429092814964, -1.2275968460944957, -1.2558119069004006] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1169  total reward: -3544.1698100433387
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7415283708947873, -1.8120763427760793, -1.4690397765198353, -1.2266154407046659, -1.111814657885517, -1.0826595367052725, -1.2419331695021028, -1.0666564253184616, -1.0730411843069692, -1.1571935353866443, -14, -1.0815822646797684, -1.1139513019665364, -14, -1.1699642044874492, -1.0587913865779814, -1.050819404343217, -14, -1.052607526227948, -1.081035170599925, -1.0510204364311675] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1170  total reward: -3546.6434194779295
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9873598780671178, -1.5918168403650033, -1.478555060262188, -1.4991919702169794, -1.563740810351176, -1.4553242303773057, -1.4375835966861754, -14, -14, -1.4733257647945806, -1.5533531177127569, -14, -1.547040703325232, -1.434056135211895, -1.4088083289059632, -14, -1.4361295196547832, -14, -1.422790030247898] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1171  total reward: -3549.7111993842373
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2585748552504903, -2.164249658948266, -1.7704128802461774, -1.657658371614607, -2.0433159327369452, -1.655057319762514, -1.7787772945815683, -1.9217761347848008, -14, -1.7038224486191675, -1.772156684459483, -14, -1.6550573197625145, -1.6561281685897253, -1.6431888969533774, -14, -1.6672546924465594, -1.7805203756594543, -1.6589715774018248] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1172  total reward: -3552.5142512551292
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8914939309937993, -2.041396128406941, -1.6102570203487518, -1.289861549146572, -1.2117308209442041, -1.2262283393453668, -1.3207199957873597, -1.224966632718542, -1.161557745186928, -14, -14, -1.2047923120821442, -1.2802160354461025, -14, -1.2746667122259057, -1.1737413502422407, -1.1528180684936853, -14, -1.173177679806858, -14, -1.159862973938548] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1173  total reward: -3554.7367715430764
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9071653079668514, -1.8371175627467102, -1.471192433626771, -1.2032832371585536, -1.1346530325819175, -1.1174201637247074, -1.2757854633331238, -1.0744421163606277, -1.0947386083183461, -1.1813252984381415, -14, -1.0938071101577826, -1.1294660209221605, -14, -1.1739190800573571, -1.0770396704537404, -1.0692240224607437, -14, -1.073353691627681, -1.1122274998089785, -1.0697022194534114] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1174  total reward: -3556.8845361370886
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8528954166325835, -2.0049504071808486, -1.4533011234307456, -1.2025513792546063, -1.1307301908965524, -1.1196255602895162, -1.2321350224946503, -1.1013345765036222, -1.0893996688508372, -14, -14, -1.1189104435815334, -1.178092466264284, -14, -1.1675193232630994, -1.0908582666021063, -1.0761557639635095, -14, -1.0876383218006982, -14, -1.078540571551284] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1175  total reward: -3559.087298092391
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9604558321438492, -2.027380219912449, -1.5396845469787064, -1.3007622963173795, -1.1939594847576238, -1.1554675554045488, -1.326044171839279, -1.118680440802166, -1.1611541142156367, -1.2866029974444693, -14, -1.153063186203537, -1.1889692393959557, -14, -1.2330756066460058, -1.13370152571866, -1.1240059642292295, -14, -1.1300558453531648, -1.1536787739151995, -1.1266061913389478] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1176  total reward: -3561.8830728533826
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.422750583074967, -1.9171349097439931, -1.7731524413185842, -1.776891845841606, -2.009003650800397, -1.6402763892889507, -1.6726186400715255, -1.7851740722498177, -14, -1.7102881752981642, -1.737090892022335, -14, -14, -1.6790266788316215, -1.7364768487335056, -14, -1.6786876590804893, -1.695674853462576, -1.6770943201895858] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1177  total reward: -3564.909835884007
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9595636502340872, -1.6084901933874114, -1.4648203525683903, -1.4382766964478857, -1.6190103437662062, -1.4057550921418442, -1.4124537757911069, -1.6000984776829488, -14, -1.4160855956150062, -1.4522155395569145, -14, -1.52928540047856, -1.398157502647099, -1.3998576086764603, -14, -1.389009071411122, -1.411306501287784, -1.3864866413352224] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1178  total reward: -3567.474122893397
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.631643129518829, -1.3698610593845744, -1.2469114593106951, -1.2098120865271083, -1.3807864693648035, -1.1744261559711997, -1.2094176724661703, -1.3578491173961733, -14, -1.2041782307472422, -1.237028385468896, -14, -1.287219705147746, -1.1863468535014199, -1.179002960564847, -14, -1.180310443149367, -1.2029366331732423, -1.177800368055229] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1179  total reward: -3569.602320533341
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6276782846648203, -1.6718404465896068, -1.3168471151491274, -1.1063395154691202, -1.0109547917183566, -0.9806601721601834, -1.146922731189522, -0.949325593450271, -0.9589565172333743, -1.0461910512989885, -14, -0.9762230219484467, -0.9948238769750343, -14, -14, -0.954122335348242, -0.9849535359993544, -14, -0.955658091951626, -0.9670862653587219, -0.953771483972538] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1180  total reward: -3571.4969473040974
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.648159758007464, -1.6560683419588969, -1.3157343392678031, -1.0837245138203877, -1.002592207473747, -0.9808938161995199, -1.1224222392437055, -0.9459004468561643, -0.9686694339186955, -1.0542352088678089, -14, -0.9677727549109216, -1.0008070644974125, -14, -1.033741236037027, -0.9513527394703123, -0.9469273052064513, -14, -0.9488949174264989, -0.9779889985011375, -0.945301177306322] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1181  total reward: -3573.5529424912042
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9431250045530937, -1.8930563000781795, -1.6190431514243917, -1.249457098633781, -1.1765253947466239, -1.195631811649624, -1.3152592127804121, -1.1173627513043196, -1.1328087936228555, -1.2089657010078458, -14, -1.1358198888219238, -1.1705150499613548, -14, -1.2080265365819598, -1.1176859860349275, -1.1083549297329345, -14, -1.1139014531673173, -1.1469684994563334, -1.1106940098003018] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1182  total reward: -3576.204950019912
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1035555182321586, -1.7239872707792592, -1.6084670575421716, -1.6096371606664495, -1.7191603429444622, -1.5908226181721496, -1.5567627068151202, -14, -14, -1.5994889353494788, -1.6837570639000554, -14, -1.6896827439359803, -1.5582584284227423, -1.5325498023981703, -14, -1.557017238634461, -14, -1.5436525989745171] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1183  total reward: -3579.807784834612
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.088019506226609, -2.34883713196704, -2.193315394564961, -2.2438974465855974, -2.4676925614400513, -2.1120777150675973, -2.0975281913290758, -2.2240278003929883, -14, -2.115242886846004, -2.1797613190323566, -14, -2.2516158422934147, -2.084308116058561, -2.0710917428175564, -14, -2.0763930895555567, -2.1392422309887174, -2.0702850123020586] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1184  total reward: -3584.315246925786
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.414201122944481, -2.7463196573341264, -2.5807041331917127, -2.5632026201076314, -14, -2.4177053037247256, -2.5117738387205972, -2.791556601653963, -14, -2.4896443696613324, -2.563609762338389, -14, -2.658759901009326, -2.4533957402626956, -2.435650657323606, -14, -2.444510644938217, -2.5048490454224055, -2.437177078872227] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1185  total reward: -3589.2342821200377
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.561135323931711, -2.8966746185109686, -2.6461822765986587, -2.6067306872308005, -14, -2.515530602522452, -2.5536975065433634, -2.7530768431595094, -14, -2.5604573811183378, -2.613460493868822, -14, -14, -2.5014108770981536, -2.583814711941429, -14, -2.5086012457114735, -2.5687773851930236, -2.5013298905268146] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1186  total reward: -3594.730494825689
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.9547681130697545, -2.9890457763819995, -3.254467536656563, -14, -3.0436049496684596, -3.0873719195563285, -14, -14, -2.9970702093587724, -3.063503977993342, -14, -2.998406490676868, -3.0136699744129833, -2.994882815124455] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1187  total reward: -3600.4214651118778
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.0974542979031776, -14, -2.9317074952458797, -14, -2.7658806185644216, -2.7826758452831455, -2.971906524921635, -14, -2.797503186914496, -2.884117814893499, -14, -2.9711764679768518, -2.753075290011119, -2.7340458231624267, -14, -2.7443817193142603, -2.8265603324341337, -2.736202173118766] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1188  total reward: -3605.853971870972
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.017454382127516, -14, -2.856948192218066, -14, -2.76314286784063, -2.7147004831199615, -14, -14, -2.78769148660168, -2.90356033590676, -14, -2.891107639155424, -2.7279696094178214, -2.692951859927808, -14, -2.713926949725225, -14, -2.698460935932157] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1189  total reward: -3610.677830852889
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9434275891129635, -2.50132045142056, -2.2498537596644526, -2.1785226925651853, -2.4854990214465666, -2.125629443837492, -2.196672059748608, -2.4093677313456308, -14, -2.185184223629341, -2.253997817634465, -14, -2.3651787295982656, -2.1457919899149123, -2.1408508168147184, -14, -2.136665991279932, -2.2138718028496576, -2.1309071219894156] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1190  total reward: -3615.153736591306
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.326803157565621, -2.6724167530765865, -2.489293617119641, -2.471393287745289, -14, -2.3341031592509633, -2.3565372631654, -2.569922089973509, -14, -2.392462022904906, -2.436536729889668, -14, -14, -2.3506770671101527, -2.4228663664642176, -14, -2.3560920256968156, -2.380767004457142, -2.3502762945791966] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1191  total reward: -3620.09820257818
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.62996559912082, -14, -2.592290463726808, -2.7577303164418168, -2.8377436361244124, -14, -2.686106241260574, -2.8035870023430367, -14, -2.592290463726808, -2.5952272417184012, -2.5836685298283157, -14, -2.624486648362445, -2.836066753959926, -2.610362827622919] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1192  total reward: -3624.408657739053
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4487931073274356, -1.921769555314925, -1.8081132886789026, -1.8438798535965175, -1.9776975903576188, -1.7716079801307965, -1.7421321894257669, -14, -14, -1.793232991573354, -1.8897650355785065, -14, -1.8777452189256454, -1.7469184974654246, -1.725057533107419, -14, -1.7414795959036287, -14, -1.7267866310451] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1193  total reward: -3628.066952363492
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.636586165798832, -2.2369277143933797, -2.042521548966542, -1.9795302552029586, -2.2498975352548696, -1.9456196359821611, -1.9793844655058426, -2.220516662832119, -14, -1.9764784692027004, -2.0347896590171057, -14, -2.1410717962939683, -1.9483621272276612, -1.9448159543909382, -14, -1.938840141810161, -1.9704050143048721, -1.9332370913313186] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1194  total reward: -3632.4243408903235
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5123194259922212, -2.810123547438521, -2.5598100345256345, -2.5449124826180816, -14, -2.4294922556458616, -2.487917302274087, -2.7314688487151537, -14, -2.473625104477, -2.5490204497812896, -14, -2.678288982889684, -2.4413829333141837, -2.425856873909596, -14, -2.4324194633615304, -2.5007811415549805, -2.424151435500028] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1195  total reward: -3637.8907837017755
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.0585520477867165, -14, -3.02028586913445, -3.2045661569348187, -3.3787801112842595, -14, -3.1191423560441223, -3.2403811939444562, -14, -3.0202858691344496, -3.028641766775416, -3.0121159722486612, -14, -3.056388028501981, -3.2594690053770763, -3.0422913759520527] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1196  total reward: -3643.5241449349983
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8260446719649455, -2.8835317178430624, -2.7516823066420617, -2.8797578623011737, -14, -2.739186167515723, -2.6262035829051946, -14, -14, -2.707215772262533, -2.8360669804571073, -14, -2.84329716751279, -2.6567653229701045, -2.624927795940526, -14, -2.641530852903055, -14, -2.6212452609740033] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1197  total reward: -3647.9392527696054
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4787879387539147, -2.0576714295321943, -1.8710276001579123, -1.8538923748333762, -2.0347859237657713, -1.8374980895739723, -1.8190245291058176, -14, -14, -1.8634358549111276, -1.9647250526264002, -14, -1.980884047605911, -1.8148876625775507, -1.7918129786601023, -14, -1.8093155657536866, -14, -1.7938625736332037] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1198  total reward: -3652.0713661448467
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3329755444417324, -2.598685132639039, -2.480846742402542, -2.5121056085288638, -14, -2.3680627201998674, -2.3769890495651773, -2.570804271355986, -14, -2.3867160736632975, -2.4474684097356882, -14, -2.535167034731152, -2.357914823074235, -2.334419710195111, -14, -2.3448460081490725, -2.391665589846357, -2.3403003965812825] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1199  total reward: -3656.4304226800155
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.852247426477362, -2.2637799706619255, -2.1121419995568607, -2.145350955554943, -2.272785489347717, -2.09824371282828, -2.0331435044591704, -14, -14, -2.0997304980968226, -2.2207525668221977, -14, -2.195895034144624, -2.0436747094897596, -2.0096605039479782, -14, -2.045167499060227, -14, -2.024636824973824] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1200  total reward: -3660.28770473256
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.535995391159465, -2.1701762857463693, -1.9590940759743274, -1.8842304785913302, -2.190720953183948, -1.8455109555419744, -1.8987977488005836, -2.0932863974883933, -14, -1.8841253794832733, -1.9350689576418982, -14, -2.0321960120104956, -1.8599968188979425, -1.8370261299321207, -14, -1.8517962340123744, -1.9039778077397336, -1.8476215485968457] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1201  total reward: -3663.4562689775366
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7398532055449294, -1.5195490819721702, -1.3902117649105303, -1.3505708393753575, -1.5040855311030668, -1.3561471546651975, -1.3484242889945197, -14, -14, -1.3911463329650924, -1.483336553215598, -14, -1.4469967443649203, -1.345484293842688, -1.321180544094159, -14, -1.34653840855779, -14, -1.3315381150446537] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1202  total reward: -3666.1809416602146
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9729517149178462, -1.6049307309765457, -1.4794013513292077, -1.4646110271476427, -1.618892925139776, -1.4220645871066981, -1.4315387768900525, -1.6321334082231118, -14, -1.4311659154292284, -1.468048904436725, -14, -1.5553589125370273, -1.415085079375542, -1.4266123758295832, -14, -1.4067628115681141, -1.4311985600666324, -1.403492138583734] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1203  total reward: -3668.857411790761
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8321549128649908, -1.4731655312719303, -1.3486698144871472, -1.3336871305604932, -1.5084617359146972, -1.2860909623367855, -1.2978769347563257, -1.4037801099757972, -14, -1.2980001943640778, -1.3342369924406228, -14, -1.394748452059893, -1.2820052831425215, -1.2686289396928174, -14, -1.276265817411904, -1.311580549552272, -1.2729779919625386] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1204  total reward: -3670.7335718913764
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6392658845289928, -0.6297661723902852, -0.7488084785810586, -0.7001935893944313, -0.5938778632411444, -0.6080587118979437, -0.606232164785137, -0.7890565319889866, -0.6045011363304925, -14, -14, -0.6522723560454291, -0.7154570043494219, -14, -0.8141653759377606, -0.6107744848445062, -0.5986247556644888, -14, -0.6168490602765998, -14, -0.6075311609223353] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1205  total reward: -3672.6585510858104
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.850837522095501, -1.4751345106080622, -1.2714175321223604, -1.4157341642127002, -1.4951987875126698, -1.3746934463718394, -1.336750688515826, -14, -14, -1.3821959385570128, -1.4463532381968152, -14, -1.4357594530954914, -1.3556119461326708, -1.340971835462661, -14, -1.3393071325694106, -14, -1.3311013311929059] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1206  total reward: -3675.6929336883823
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.44893878437785, -1.9773206639131378, -1.8467133255604617, -1.8512802177542298, -2.0237973621577305, -1.8151467124030447, -1.7767496662785487, -14, -14, -1.829421841278478, -1.9418983513689667, -14, -1.9213869569821005, -1.784781321794723, -1.7594235641740963, -14, -1.7829760324202135, -14, -1.7629650704493194] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1207  total reward: -3679.926306196834
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.399348953408339, -2.804445057214251, -2.61580859988905, -2.5676320594653186, -14, -2.462348110467346, -2.544237440795252, -2.9276698017192957, -14, -2.5247442361371246, -2.5939460448977933, -14, -2.7058597042444306, -2.492460978846366, -2.512336780938581, -14, -2.480428862378901, -2.5455115325419904, -2.473948944277794] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1208  total reward: -3685.2973254600056
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.0868826176903945, -14, -2.8941323917833466, -2.9104508450419675, -3.1435246236754097, -14, -2.9591738063414468, -3.009917301163665, -14, -14, -2.911796102951998, -2.970673833726858, -14, -2.9141010686875846, -2.9616700047201645, -2.9086711527039415] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1209  total reward: -3691.3564349966973
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.338685945372824, -14, -3.2392357215221916, -3.2200234754063093, -3.510320285449994, -14, -3.231403964878751, -3.3275479048330507, -14, -3.5306880780774526, -3.188767414546295, -3.1735443621257002, -14, -3.174307879594106, -3.2491655893435376, -3.16497714490864] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1210  total reward: -3697.8512391133463
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3156555073213774, -3.412635143564302, -14, -14, -3.401135358038324, -3.4966653128325205, -14, -3.594758934275463, -3.3535954652983606, -3.3188815752830148, -14, -3.337461486371201, -14, -3.329826971740314] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1211  total reward: -3704.183482846209
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.173490899916184, -14, -2.999158896383185, -3.0260691110430264, -3.236879517173093, -14, -3.0853016183599147, -3.1554605051062796, -14, -14, -3.0191971249118223, -3.0944496729684268, -14, -3.025946588718453, -3.064737885994286, -3.01658822554152] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1212  total reward: -3710.7651523895793
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1213  total reward: -3724.7651523895793
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -4.12838180996149, -3.4199676953177605, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1214  total reward: -3730.9749056552073
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.176500655411881, -14, -2.957122824459295, -14, -2.8048695762166522, -2.830747272432661, -3.0052511944272386, -2.9165879674030126, -2.8552141027844584, -2.9293421158515356, -14, -2.998507903567465, -2.7664189365717515, -2.8191307532170264, -2.846553390512977, -2.801264295571522, -2.8404142951787943, -2.7897855703098338] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1215  total reward: -3735.7847060843633
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8132982184108806, -2.3445409080958095, -2.15627953531144, -2.1089678159662633, -2.366534496017332, -2.0571890011228433, -2.092597677165421, -2.3481315638628963, -14, -2.0934714099124663, -2.152282716015671, -14, -2.2677625138559896, -2.059635047998006, -2.0607603507785486, -14, -2.047720851659202, -2.08328540559846, -2.043381492584715] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1216  total reward: -3739.944256533865
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.85418362921312, -2.4656697044571656, -2.2301132168575606, -2.152493846181288, -2.442162933747426, -2.112052669668923, -2.1832843666845827, -2.4986356844556514, -14, -2.172906014729838, -2.2483382042597913, -14, -2.3638718944208366, -2.1329106642632096, -2.141798831461259, -14, -2.124435791067019, -2.153172748746131, -2.11616895691687] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1217  total reward: -3745.5431991511764
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.390569970420554, -3.489893224779624, -3.618258801382005, -14, -3.5307870734759903, -3.5832746335815506, -14, -14, -3.497866754645759, -3.531101880572769, -14, -3.4912345557946027, -3.5096472488089687, -3.4868899476426156] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1218  total reward: -3752.0754098786297
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.1649370633848894, -3.2092150170287495, -3.5544160143189236, -14, -3.2030048748256488, -3.297169874762151, -14, -3.4524362223409573, -3.1642406506545644, -3.139623751117981, -14, -3.1521012165430684, -3.2016975743004634, -3.141640757032786] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1219  total reward: -3758.2259697438876
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.185118974209996, -14, -3.037494758884713, -3.0632073847736945, -14, -14, -3.1085446112680692, -3.2687093379436223, -14, -3.2516341788939647, -3.047424772729581, -3.0191820790013177, -14, -3.0385935732471054, -14, -3.0109361141397932] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1220  total reward: -3764.4739554520534
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3709991947856803, -3.2489951242843422, -14, -14, -3.3315770210863147, -3.4586515661495785, -14, -3.52906987236236, -3.279058361909296, -3.248971642993906, -14, -3.2547442062664476, -14, -3.2370495940256756] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1221  total reward: -3770.0503134811875
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.303522300958558, -2.68190245297748, -2.4555313934172, -2.442103709555179, -14, -2.4078828790633326, -2.3613190795540473, -14, -14, -2.4216995584708503, -2.535706174971252, -14, -2.5641603173153915, -2.370848561240399, -2.349319104904385, -14, -2.3557328162785387, -14, -2.339308435108678] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1222  total reward: -3774.710382906685
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2016402468275498, -2.6141048761987364, -2.4074432883732926, -2.421497669681571, -2.5499418999283647, -2.4190648270269595, -2.3329650065305376, -14, -14, -2.417537954139683, -2.5534044251678387, -14, -2.5539661879310565, -2.3390394239424497, -2.2935769846196896, -14, -2.340663304286355, -14, -2.3207609903888295] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1223  total reward: -3780.2608144751325
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.256480675287305, -3.3849794819177026, -3.2204956789003067, -3.3850341073828734, -5.1967849962623935, -14, -3.2918289993502765, -3.3159050841660505, -14, -3.6129268681016082, -3.256406234930151, -3.5553480828763635, -14, -3.2570944848684937, -3.2530069409892435, -3.2568545838275855] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1224  total reward: -3784.9082039211794
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.417939969374016, -1.410170561960849, -1.701323765846357, -1.6269273315042776, -1.4372337978423602, -1.421579705471456, -1.480455377552184, -1.1054068065066345, -1.7249614403474922, -1.6304012084323605, -14, -1.4546805099417823, -1.4918919240871102, -14, -14, -1.439710682085781, -1.453541016700143, -14, -1.4293878065507564, -1.4329019270650682, -1.426893767146682] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1225  total reward: -3786.8851716138247
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8815621774375514, -0.8717298899270395, -1.1521132605870885, -1.015471951282493, -0.8707594124524785, -0.8795969244009011, -0.8831786769269434, -1.125826149564976, -0.86966706170718, -0.9280751139325877, -14, -0.909485218974106, -0.9583371010473597, -14, -1.1527904413681234, -0.8733467394891808, -0.8749454463626118, -14, -0.8772818600905057, -0.9509904374571713, -0.871560886138942] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1226  total reward: -3788.5046085937142
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7579312335415354, -0.7505212158546954, -0.9118422147043076, -0.8749488093737826, -0.7491178488980089, -0.7471908645653698, -0.757994549801804, -1.0590854952398134, -0.7475183885890131, -0.800827569436554, -14, -0.7879440519062223, -0.8496811117412826, -14, -1.5441981149375157, -0.7474103472800702, -0.738608041478322, -14, -0.7576087924577679, -0.8561613181728642, -0.7497699181819641] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1227  total reward: -3789.995550179935
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7840244324258134, -0.7732780342122965, -1.0070523135291392, -0.8407152200515204, -0.7390556616416856, -0.7829457084199318, -0.7505000682070374, -14, -0.7530078413499147, -14, -14, -0.7911607649127593, -0.8501057990998968, -14, -14, -0.7548054071957715, -0.7398592635463015, -14, -0.7617404768702053, -14, -0.752333544742771] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1228  total reward: -3791.4400910181953
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7071702974709668, -0.7038854859836388, -0.8877244195234933, -0.7751849491971411, -0.7154555698832006, -0.7146211601503756, -0.7165373929682728, -14, -0.7088499055500164, -14, -14, -0.7446562276693238, -0.8013679629778538, -14, -14, -0.7181325990461174, -0.7135624610745979, -14, -0.7140845279896276, -14, -0.7054851766182101] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 1229  total reward: -3792.87334369005
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -0.728324731475906, -0.8343144530341986, -0.7891649068870132, -0.7665497605900632, -0.7305916948362973, -0.7334825019555965, -14, -0.7314396000725828, -14, -14, -0.7827241451119151, -0.8711062142240783, -14, -14, -0.735695410117564, -0.7173142446711028, -14, -0.7447698126494814, -14, -0.7293671858716129] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1230  total reward: -3794.5951467144873
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.0078936918140513, -1.2355913147564694, -1.1326801067418222, -1.0430940873336223, -1.00628343430806, -1.012112860313819, -1.4488745386952757, -1.0026484988301627, -0.9985789173504094, -14, -1.0510903136349579, -1.1194083094738343, -14, -2.0823219930741828, -1.0113349731151335, -1.0111927937808165, -14, -1.012188100658558, -1.0913285022464025, -1.0044887797657673] argmax 9
Action chosen: switching off line 9
  Simulating cascading failure
  ok
timestep 1231  total reward: -3796.653838505477
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.059722029500058, -1.2619027851041595, -1.1931659797336291, -1.1309488687543008, -1.0591718557632945, -1.0731455391123703, -14, -1.0640755284274708, -1.0709573186981778, -14, -1.123986794049837, -1.1972953274190687, -14, -14, -1.0601049634676825, -14, -14, -1.0683982762056488, -14, -1.060112873639045] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1232  total reward: -3799.213850462882
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.4996160114895416, -14, -1.5178428029954527, -1.5254482292404996, -1.4423408993471127, -1.5014737650350212, -14, -1.490268732959473, -1.411635739319956, -14, -1.60250029097013, -1.7476505375224094, -14, -14, -1.4856512967354811, -14, -14, -1.5225117328614952, -14, -1.5008401016426924] argmax 9
Action chosen: switching off line 9
  Simulating cascading failure
  ok
timestep 1233  total reward: -3801.814790341833
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.190957422942808, -14, -1.2850371540840748, -1.2092635492778645, -1.178487033643804, -1.1963873922245845, -1.8032914244681468, -1.1902982277916714, -1.218007420027824, -14, -1.2426057148188525, -1.3123090567531166, -14, -2.417583702272508, -1.1957436649403883, -1.2019289017205241, -14, -1.1964024511014433, -1.2755821242386767, -1.1893041396308452] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1234  total reward: -3804.3308705763884
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.3447734302673717, -1.5611419373923927, -1.4632065016646034, -1.3506126300261203, -1.3374695365674871, -1.3517967834842615, -1.9343788027754716, -1.3334785221430356, -1.3620924390747897, -14, -1.402943153669462, -1.5086043107592055, -14, -2.861057656895177, -1.338370238292986, -1.3236265676962131, -14, -1.3507176517610322, -1.5128179776844857, -1.337593200911565] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1235  total reward: -3806.97226732495
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.3169275806703349, -1.5194554428707612, -1.4245914152647812, -1.3844497095305797, -1.3221533584537533, -1.324972034934343, -14, -1.322899330391979, -14, -14, -1.4161281405606931, -1.5706179761148693, -14, -14, -1.3306514946654509, -1.2998697601535687, -14, -1.3433089636151057, -14, -1.3177701808648596] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1236  total reward: -3809.480561777824
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.2152444665045972, -1.4711826244547204, -1.3103358593348566, -1.2116701008253734, -1.224495691490553, -1.225978192668552, -1.9922501787356333, -1.2114019294208913, -1.2794365122724292, -14, -1.2623479363026302, -1.3411866899416456, -14, -2.288965947097732, -1.2136840569333713, -1.2059004923766523, -14, -1.2172534397580892, -1.3065234816215594, -1.2084246927206312] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1237  total reward: -3812.0943750473925
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -1.40817290794493, -1.5962898473534808, -1.501470678081793, -1.4603915277736108, -1.413682966586786, -1.4158864059832275, -14, -1.411750550891055, -14, -14, -1.5070986703984324, -1.653062597745709, -14, -14, -1.4207665301670953, -1.3899835248999215, -14, -1.4304447487894023, -14, -1.407912777191968] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1238  total reward: -3816.516573714127
 Simulation with line 0 switched off
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
rewards [-14, -2.081393293292355, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 1
Action chosen: switching off line 1
  Simulating cascading failure
  ok
timestep 1239  total reward: -3820.581005824116
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.700843661504401, -2.381682081033398, -1.8695567406355087, -1.9920765007710584, -2.2755857584894628, -2.2795141160856973, -1.8939788434521831, -2.440605420070613, -14, -2.0484123036979622, -2.1753485690061365, -14, -2.279514116085702, -1.9581630022868854, -1.971529186227162, -14, -1.9979524563982212, -2.2337256763801845, -1.983038816696425] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1240  total reward: -3823.7020202287986
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.0199069376911414, -2.2256759637097394, -1.7073394792455356, -1.447013070346574, -1.3130599450812945, -1.2820826821197635, -1.4177813555665375, -1.2344112366421698, -1.2190285592304309, -1.529131225898963, -14, -1.284565160847732, -1.3412833873511936, -14, -1.9135747447591729, -1.2608637863835193, -1.243807118982638, -14, -1.257498176390426, -1.3188663351683934, -1.2514576640473147] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1241  total reward: -3825.9977754141655
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8234083829225989, -1.878446987068908, -1.4891761303922062, -1.2355127856540675, -1.1379814195622653, -1.1138046749495303, -1.259650884567866, -1.0909686884718222, -1.0995122374703732, -1.212282180021793, -14, -1.101220317707379, -1.133932867555557, -14, -1.1968195001017625, -1.0849186110939277, -1.0832866834603085, -14, -1.0796525883159136, -1.1050073029068812, -1.0767266261362833] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1242  total reward: -3828.211146678025
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.868976082070206, -1.9609614627705958, -1.6723148565292567, -1.309891705715701, -1.1989189744881825, -1.206957281380302, -1.319995641347924, -1.1517868089359786, -1.1580459239669685, -1.280877573842153, -14, -1.1582157714540506, -1.1873885608772436, -14, -1.2525811479766804, -1.1457086831742156, -1.138132122856153, -14, -1.139110309474012, -1.1573533838082222, -1.1366446377235069] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1243  total reward: -3830.5733491507717
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7241980916806854, -1.4333892164638637, -1.3006267447148667, -1.2640125392588144, -1.4654766805639239, -1.225550332436668, -1.2562481551671016, -1.3623312456563517, -14, -1.2548621849820258, -1.2983248954842428, -14, -1.3385239121374264, -1.2339897301760812, -1.2272854402346012, -14, -1.230153177302693, -1.278734133547845, -1.225557835023147] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1244  total reward: -3833.051202722102
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2501158248073236, -1.2441807435681027, -1.4607239027057868, -1.3881040079881872, -1.257382785836328, -1.2505072204047245, -1.2787966594251894, -0.9572235442035893, -1.5210941011462342, -1.3487818263435127, -14, -1.2750695504771854, -1.2993563929864895, -14, -14, -1.2601157086148391, -1.3276087525965508, -14, -1.2530136894024169, -1.243410860439156, -1.2523032388930018] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1245  total reward: -3835.9457761991816
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6140907160928726, -2.2352082513493023, -2.053916292190388, -1.9790859356593873, -2.2900157568873327, -1.9399076099360248, -1.984980731568684, -2.211893274090211, -14, -1.9892684304489594, -2.0538410256876953, -14, -2.1228892139363937, -1.951618365160033, -1.957083216018111, -14, -1.9428128996158842, -1.9937399893131262, -1.9373499328764174] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1246  total reward: -3840.2047947201518
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2294461849058047, -2.7223072504156516, -2.4524060247087287, -2.3811567316388724, -2.7206000174897955, -2.3537245525810047, -2.369140569215894, -2.611842628187486, -14, -2.3809144492420797, -2.453477036333812, -14, -2.5774198748629873, -2.3417641273806007, -2.3298466303535794, -14, -2.3274153053415656, -2.3669204676736832, -2.3216685880937415] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1247  total reward: -3845.7456354817778
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2487064640538943, -3.2846847973288105, -3.5018389757078943, -14, -3.290958940610088, -3.40078779998906, -14, -3.527212933364058, -3.2381407471442016, -3.204879506194231, -14, -3.2309197742103026, -3.335779403963713, -3.2191721735319208] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1248  total reward: -3852.3958781281062
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.546144508230326, -3.4700392491382646, -14, -14, -3.561590171045957, -3.7286321150558117, -14, -3.7427465933521553, -14, -14, -14, -3.470486815000408, -14, -3.445363140134428] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1249  total reward: -3859.076596589839
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.361147869514336, -14, -3.2731521811169277, -3.2960381104935994, -14, -14, -3.3544744207553734, -3.521925482501159, -14, -3.5325994996621275, -3.278038586431952, -3.251806869322721, -14, -3.2599207645256865, -14, -3.23535532159801] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1250  total reward: -3866.8800450518943
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -4.4198452615654436, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 6
Action chosen: switching off line 6
  Simulating cascading failure
  ok
timestep 1251  total reward: -3874.027157966922
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.7492963270387705, -2.4554431266378045, -2.8350738843667784, -2.7370340273787437, -14, -14, -2.8328774545635866, -2.996768690235871, -14, -2.9631687352903064, -2.786986667121567, -14, -14, -2.754027912303596, -14, -2.727267653462375] argmax 6
Action chosen: switching off line 6
  Simulating cascading failure
  ok
timestep 1252  total reward: -3879.425382343281
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.251945771086877, -14, -14, -14, -3.0481737728091853, -2.9511482738365773, -14, -14, -3.045049176027952, -3.2145903355375696, -14, -3.1665086378659844, -2.9796960280316593, -2.9348972571133367, -14, -2.972351644494612, -14, -2.9427812497208397] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1253  total reward: -3884.679520712047
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.243758824454146, -2.6460619608147153, -2.454999854905847, -2.4181470970692023, -14, -2.321122173298805, -2.376852645576515, -2.6184228733322583, -14, -2.376937090520696, -2.4458340217301076, -14, -2.540333660143534, -2.3360102302141796, -2.328949575549351, -14, -2.324163140409372, -2.3874787651806364, -2.319241111653195] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1254  total reward: -3889.2585429205487
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.201420596077478, -2.6258532047098004, -2.403550718327992, -2.3455740628213166, -14, -2.2671400062676117, -2.309291510562581, -2.4531380056996355, -14, -2.3097753884177203, -2.382536943949054, -14, -2.4563782840663735, -2.272267373367175, -2.2415468595265535, -14, -2.266468530689385, -2.348210405075761, -2.259781096848342] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1255  total reward: -3893.679293514021
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0592492910496794, -2.4489124357183694, -2.2566140991291728, -2.2953236532238335, -2.3679976679981816, -2.250140881995441, -2.193867956249831, -14, -14, -2.2624121405626907, -2.3804566303714503, -14, -2.376256370110951, -2.191456310002673, -2.148537495272943, -14, -2.196701591691494, -14, -2.17920373394547] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1256  total reward: -3898.464245000201
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.820554967736123, -3.0336214956572896, -2.7885479690259976, -2.7842569870229066, -14, -2.6936530026836714, -2.6818203870280524, -2.8546612623112835, -14, -2.712571974295895, -2.805912527915486, -14, -2.9289898503320724, -2.6542711467435316, -2.636475209004149, -14, -2.643840580704254, -2.7092562344689437, -2.636413990907409] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1257  total reward: -3903.879893358372
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2140839556816463, -2.9345714707615524, -2.8880095933243304, -14, -2.8262306241716746, -2.8307656466672535, -3.1110039404753467, -14, -2.836205690393495, -2.9130340381967432, -14, -3.0798302783644007, -2.801907404586296, -2.790454910101858, -14, -2.785800460032656, -2.8456019688930088, -2.7792343672638204] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1258  total reward: -3909.9737677745134
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.3217589723739724, -14, -3.3006736926115847, -3.4302345633318057, -5.106415989324621, -14, -3.3485300191296936, -3.3671263611663957, -14, -3.736913670381767, -3.318958317524985, -3.540904999148065, -14, -3.313367560674397, -3.3077397962195083, -3.3146400488772385] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1259  total reward: -3915.4321554938238
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0983454393249565, -2.5267481630024844, -2.2900684410621968, -2.242684792451265, -14, -2.1417275286545747, -2.158857105006424, -2.3231373212932795, -14, -2.2035326966087094, -2.2458398629228973, -14, -14, -2.1588609297104355, -2.2088721813598817, -14, -2.162148530275453, -2.183451260048564, -2.157714026698866] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1260  total reward: -3919.7645997859463
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1548818708410615, -2.540583858854445, -2.327155483840826, -2.294582268520856, -14, -2.224284226088741, -2.228241442278079, -2.353902967665905, -14, -2.2475797525279466, -2.3240622605564867, -14, -2.3976924466126674, -2.2041091365913013, -2.1793970474554567, -14, -2.1972255189773517, -2.269816668332674, -2.190716763467648] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1261  total reward: -3923.468791265963
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5840446663275114, -1.5622426198074368, -1.7986266648727418, -1.6573334917825342, -1.4997085820021325, -1.5384680021846073, -1.5219004290852958, -2.1522897028966854, -1.5290234335493011, -14, -14, -1.6107829316168027, -1.7424225491918968, -14, -2.0310245034045953, -1.523772348840487, -1.4857692265113942, -14, -1.545987688261274, -14, -1.5247944325613252] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1262  total reward: -3926.87080489407
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.779837211999029, -2.267170503347964, -2.0191020885672035, -1.987703154017731, -2.2166573645950063, -1.907245735288348, -1.9735795160561065, -2.2475332644527555, -14, -1.9602261459247332, -2.0208187339117547, -14, -2.108198552413727, -1.930332496401475, -1.9305851848664772, -14, -1.9226408780749016, -1.9548860664686774, -1.9162444015953028] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1263  total reward: -3930.242887572099
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1012874688295518, -1.6995426382437906, -1.5561419655294488, -1.5294116477082782, -1.772406101365771, -1.4719087479329942, -1.4856605562767022, -1.5896231757783874, -14, -1.4968319116589077, -1.5281331132374782, -14, -14, -1.465631078060101, -1.4909506869191442, -14, -1.4691568557917833, -1.4959391876653119, -1.4648369427409504] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1264  total reward: -3933.0712348957672
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9480225565292666, -1.578336198901729, -1.4502846512361034, -1.42364953294634, -1.6666636682168312, -1.3600334543140633, -1.3676792541022609, -1.478628268438106, -14, -1.3885623089480386, -1.4178420975537958, -14, -14, -1.364620070845334, -1.3986401358273142, -14, -1.367772799901823, -1.3924040805311062, -1.3635103809272031] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1265  total reward: -3935.522608449208
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8833441251964664, -1.9492529998846728, -1.5049957907825355, -1.2568531436848702, -1.1553670913480367, -1.1247220475302497, -1.2794068535804124, -1.093094659663462, -1.1182952675177613, -1.2419688984751727, -14, -1.1125149697956112, -1.1402690978402197, -14, -1.1965629121136954, -1.0992205104874677, -1.0931063733430622, -14, -1.0933806014324394, -1.1250029907818702, -1.0913400991268702] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1266  total reward: -3937.6701213713227
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.781164964191484, -1.845273604129796, -1.5142036611393395, -1.2354389602142708, -1.1197195793384436, -1.0975160190341537, -1.255361713013704, -1.0587239859252813, -1.0812384501861505, -1.169508395742657, -14, -1.0808741747296653, -1.1151758086783288, -14, -1.155316433076896, -1.0624871689578104, -1.0533052992471055, -14, -1.0593586714791206, -1.0913397635223019, -1.056172822987992] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1267  total reward: -3939.9592489840074
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.697686130007467, -1.3868594174391724, -1.3009242120832878, -1.2909772312616246, -1.4616497198792846, -1.2593282066517382, -1.2574460868369288, -14, -14, -1.2734271018692986, -1.320543404876547, -14, -1.3657783460746344, -1.252492210866562, -1.2455824883284055, -14, -1.241831574365573, -14, -1.2358223134372863] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1268  total reward: -3942.866329509049
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.238574922353288, -1.9064877663544757, -1.7435950850786053, -1.7104985437670222, -1.8890486918888112, -1.7203127325995184, -1.689752094981029, -14, -14, -1.7361882682740963, -1.8354416421989825, -14, -1.8434296617025363, -1.6905061334482654, -1.665356099789778, -14, -1.68721262191306, -14, -1.6712582116046457] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1269  total reward: -3947.2572179623435
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -2.8076822088005, -2.747863251613101, -2.8755085867417916, -2.7034011732969616, -2.825999355596397, -4.203600683005142, -14, -2.7526774992375653, -2.7719845327539296, -14, -3.0464831274113617, -2.7326078628850947, -2.904779853074293, -14, -2.7252627741286033, -2.7198583228424167, -2.7255323535046645] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1270  total reward: -3952.665750665535
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.1052760919654934, -14, -2.8195434093897176, -14, -2.7042279542163987, -2.724214899922791, -2.946399320413422, -14, -2.7639541645570898, -2.8143293439188746, -14, -14, -2.706953576805722, -2.7678196757396343, -14, -2.710070700473891, -2.7640285245202088, -2.705131529894552] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1271  total reward: -3958.2514721641837
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.304976270060818, -14, -3.014621999892388, -14, -2.908390291886034, -2.9387741393954836, -3.245948260623646, -14, -2.9471046984961577, -3.040348362404563, -14, -3.1599821274616278, -2.9019981178244625, -2.9120838474729576, -14, -2.891144611655527, -2.964634169725121, -2.8814935444321974] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1272  total reward: -3964.464460425122
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.3086152996198246, -3.423455400247534, -14, -14, -3.4079688725721535, -14, -14, -3.60566528214291, -14, -3.3261126417163167, -14, -3.342195597692705, -14, -3.331494716506489] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1273  total reward: -3970.6027203932717
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2330322747771096, -14, -2.9525102078927716, -14, -2.8167903310955382, -2.8445322594436018, -3.1415083087075013, -14, -2.8848041478458577, -2.930644243423946, -14, -14, -2.829619385778338, -2.925862625241593, -14, -2.834099758211816, -2.865296681548327, -2.8296446685296046] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1274  total reward: -3976.7249078812733
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -3.570733808644743, -14, -3.274931614480111, -14, -14, -14, -14] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1275  total reward: -3982.807808329181
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8864999376349454, -3.109695056696618, -2.9368081116368807, -2.9719247388317993, -14, -2.951203014743506, -2.8180631738770985, -14, -14, -2.896430117691204, -3.023290111638923, -14, -3.104313473734592, -2.8427826271106915, -2.806814639980479, -14, -2.827002719277174, -14, -2.8079688334274366] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1276  total reward: -3988.296577481777
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.75452185770052, -3.082838988840143, -14, -2.786286258518611, -14, -2.696912750017516, -2.7387865419678215, -2.9761678989418847, -14, -2.7401360410064224, -2.8202685552004456, -14, -2.925477960746033, -2.7002717055603913, -2.6692781612082186, -14, -2.6886574152464267, -2.7619648448070615, -2.681954512615539] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1277  total reward: -3993.2482307932623
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2059831761109745, -2.5544607115863807, -2.3913112783685997, -2.4143898000311435, -2.6258161635135124, -2.3333718726957144, -2.309897320445805, -14, -14, -2.3635237423149027, -2.4945444595870216, -14, -2.4938300495144827, -2.3102450970434307, -2.2842545207957494, -14, -2.304642621054224, -14, -2.2823751502768017] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1278  total reward: -3997.5228440203305
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.7353031460859607, -2.2346137387212166, -2.0794275672096516, -2.079383496472134, -2.2420506034276513, -2.0562282812316424, -2.0058931542257903, -14, -14, -2.0658352945110416, -2.185826030115101, -14, -2.171962352257886, -2.012651400265663, -1.9794494070024808, -14, -2.0128279925094246, -14, -1.9922380767913503] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1279  total reward: -4001.708907041913
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.097544254146829, -2.531179942847508, -2.330256442011466, -2.297326224391158, -2.569765606871561, -2.20676786580377, -2.2684600154225065, -2.531237824520602, -14, -2.2635909084400625, -2.3331537912844, -14, -2.442813291096141, -2.223168324743159, -2.2162201191189093, -14, -2.212357909333902, -2.255870386211989, -2.206613614580305] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1280  total reward: -4006.3056296954865
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2283567589376285, -2.750586855488921, -2.516065165406744, -2.4445806226397027, -14, -2.372137297266188, -2.477765369646327, -2.7994024982649166, -14, -2.4530196208496844, -2.529716822669896, -14, -2.671712382940015, -2.406461284049573, -2.422035431285236, -14, -2.396909767419867, -2.4625885065319335, -2.3901090389933626] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1281  total reward: -4011.1469812994137
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4295234380145114, -2.8600635551941664, -2.6127753586189173, -2.546708598581992, -14, -2.4317315019324903, -2.466171371721204, -2.723933720852578, -14, -2.513597517122037, -2.545572341937515, -14, -14, -2.467333794850354, -2.542847664620047, -14, -2.4707403537459993, -2.4812557143526868, -2.469214306660553] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1282  total reward: -4015.7850456884244
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2703424996478394, -2.4974664480506767, -2.3344395049172526, -2.38727797294732, -14, -2.2307232275384967, -2.247367170585306, -2.399379154702941, -14, -2.2608351411086622, -2.3369127609451694, -14, -2.4135654762067293, -2.220840456054804, -2.212696256861718, -14, -2.2138862506385624, -2.2857697479388044, -2.206332887078409] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1283  total reward: -4020.9959141137233
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -3.0913208646085524, -3.034386302683515, -3.169418186717877, -2.9825834007938767, -3.119371336910981, -4.556151798833036, -14, -3.0299458525623537, -3.0464848171308496, -14, -3.387429056942541, -3.0140405978620004, -3.1498605547129874, -14, -3.003649228503554, -2.997706293938386, -3.0045355382208196] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1284  total reward: -4026.661018408886
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.8523942825594575, -3.017452050771129, -14, -14, -14, -2.6836206713422928, -2.6933095772086872, -2.864814324003501, -14, -2.734931309620237, -2.7860081735738547, -14, -14, -2.6856838807561663, -2.704017878048677, -14, -2.688070074645912, -2.7322705251647608, -2.682520894368484] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1285  total reward: -4032.662357678966
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1286  total reward: -4046.662357678966
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7562444798074202, -1.724525006672045, -1.6053210413346357, -1.3833714709666678, -1.1328199962311927, -1.2123567264504604, -1.3267038355503051, -1.199154392427762, -1.2196554415017615, -1.3318976001197216, -1.2624408272752123, -1.2243744309088067, -1.2577676051132904, -14, -1.307368454877917, -1.1841558052846912, -1.1990934492080851, -1.2312043010466363, -1.1993482236492679, -1.2297053700067417, -1.1951176368636707] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1287  total reward: -4048.8223662982527
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7589430114239308, -1.8172691324581471, -1.4326816133021367, -1.1939084484144953, -1.0888472852329536, -1.0582310168063944, -1.1899124711552043, -1.0157078178792192, -1.0535173994981137, -1.1473756787913003, -1.0733624165805917, -1.0524269445384555, -1.0761264691084784, -14, -1.1138127567444196, -1.0195039567227056, -1.0391405532927518, -1.0488057033932405, -1.0298785494536915, -1.051305674575379, -1.027188623055081] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1288  total reward: -4050.6298489472165
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3340263825441459, -1.3733983364150841, -1.127808533795241, -0.9108494975167161, -0.8374675492929624, -0.8285306252929487, -0.9316907412390909, -0.8005973834636322, -0.8060747818405571, -0.8554776051703596, -0.8240991079528043, -0.8120050445868561, -0.8244764620906586, -14, -14, -0.7928946525533747, -0.8087072257923382, -0.8057267895800212, -0.7937451248591519, -0.8035382839371514, -0.791774831085112] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1289  total reward: -4052.144624808295
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2225642474813028, -1.2617190702505043, -0.9741603377798845, -0.8443850044453115, -0.7664208467406249, -0.735018199969849, -0.8610268480578829, -0.7206579190056773, -0.7241893736490153, -0.7806667303733232, -0.7432465693903573, -0.7411219778614562, -0.7516155746947084, -14, -14, -0.7233050944200343, -0.7463309723450704, -0.730172830803296, -0.7245745092270558, -0.729176526075037, -0.7230010299927626] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1290  total reward: -4053.6364192851397
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3563629977522293, -1.3572962057541802, -1.0760460425219263, -0.8926417243016783, -0.8200410642049277, -0.7963842360109618, -0.905492285750232, -0.7740444873009211, -0.7828052856468726, -0.8441046081948106, -0.8006284481126674, -0.7877318244819619, -0.8041542809644913, -14, -0.8274299616193727, -0.7648420094688781, -0.7782222031266013, -0.7840058628189256, -0.7730264580710395, -0.7853866463750364, -0.771136557839767] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1291  total reward: -4055.1824277164833
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3221405026868578, -1.3413752134756127, -1.126520390781926, -0.9056710281640518, -0.8282038218234475, -0.8184568103609919, -0.9314063050686603, -0.7796992740641593, -0.8017809867775553, -0.8669133110842023, -14, -0.8006731043550114, -0.8290557156564649, -14, -0.8535893912215035, -0.7863952226152948, -0.7795927992301749, -14, -0.7841891193387606, -0.8096998086290225, -0.7811664218742801] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1292  total reward: -4057.1257356636324
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.953280820436406, -2.06016336681357, -1.6893786068661936, -1.2977230320717197, -1.2211648950323568, -1.2578029765498493, -1.3534756887417776, -1.1950681412408728, -1.1725272153368327, -14, -14, -1.2029996592830623, -1.2636755465032996, -14, -1.261201844684524, -1.1785621415029783, -1.1657081221934322, -14, -1.1735740178241743, -14, -1.1637151479188603] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1293  total reward: -4059.710686619018
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9762759832172592, -1.5896408553062724, -1.4858477125400509, -1.4959478643662119, -1.6141670311043246, -1.4534778295551132, -1.436317811182266, -14, -14, -1.4823179003397424, -1.5825900799824222, -14, -1.5460148682804569, -1.4374272648686328, -1.4142230941615705, -14, -1.4385582420752263, -14, -1.4212358074663884] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1294  total reward: -4062.937452230208
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6941530620965977, -2.044530764351329, -1.917160606716647, -1.9696034723466227, -2.1381824988509517, -1.8500417190021103, -1.8384149242688308, -1.9924928793626429, -14, -1.8477867138279835, -1.8953046436005878, -14, -1.985057392764472, -1.8253598287727353, -1.8092336956095427, -14, -1.816289521530256, -1.8493303989842316, -1.8125425170283744] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1295  total reward: -4067.1187498125864
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.9729295775284346, -2.6268197897162877, -2.3690910569218016, -2.3953076800110424, -2.298439925740081, -2.5035733004720546, -2.373263880428084, -14, -14, -2.4245934412434798, -2.5084276665992884, -14, -2.5846496248655133, -2.3011753740224985, -2.226984817397858, -14, -2.386147779186306, -14, -2.37206388676966] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1296  total reward: -4071.098998846857
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4338196305777267, -2.0334435731851435, -1.8580149594171615, -1.8059358689749567, -2.0755427613956066, -1.7672782971916259, -1.7910146997018477, -1.9666564089463383, -14, -1.797371819032043, -1.8469560834437122, -14, -1.9280253352464256, -1.7662733588966206, -1.7521304951574537, -14, -1.7560045638520818, -1.7949554014778237, -1.753264216872511] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1297  total reward: -4074.984079726384
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4066084486150063, -2.1451966256842883, -14, -14, -14, -2.2539373603527904, -2.137325533583566, -14, -14, -2.200347838283979, -2.3033444609028284, -14, -2.355628315943291, -14, -14, -14, -2.1495017182313862, -14, -2.132950384369486] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1298  total reward: -4079.0157083036984
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.728805086388887, -2.149980655471961, -1.9850144306885913, -2.0161906612849227, -2.1756489347312438, -1.9457345173512983, -1.9200373062837486, -14, -14, -1.9753138754178932, -2.0893539729151636, -14, -2.0782421417474297, -1.922064435237771, -1.896768680311504, -14, -1.9164948884959143, -14, -1.8986781929447585] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1299  total reward: -4083.477172095913
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.896091614514348, -2.7256401514529602, -14, -14, -2.595742894624862, -2.5901771730432244, -2.770832930427842, -14, -2.6108598919753305, -2.677228160124048, -14, -2.7103457457338362, -2.5820624774923013, -2.552424219589645, -14, -2.5703555301616534, -2.617846236052595, -2.564695111902804] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1300  total reward: -4088.373495271618
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8159482482386333, -2.5536804948306426, -2.33343561795441, -2.3500067401987375, -2.2396963488111767, -2.452541481415804, -2.346359627618703, -14, -14, -2.409097322069133, -2.50950462126202, -14, -2.5325185424699206, -2.2493133484364747, -2.1658577096751253, -14, -2.3601643307895124, -14, -2.3438989561156918] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1301  total reward: -4092.0405264001397
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.091319899747092, -1.7511015491004513, -1.592610463532752, -1.5436797985368447, -1.782707134213572, -1.4928017187528975, -1.5434629656967689, -1.6912949007188756, -14, -1.5361501260395123, -1.5861826443279408, -14, -1.6343996315008134, -1.5102834296723286, -1.5049047974927434, -14, -1.5061827522922067, -1.563604173153252, -1.5011734188467465] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1302  total reward: -4095.700736456916
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.373841797847899, -2.293414005165125, -14, -14, -2.0843171111104093, -2.1937731135825294, -2.2021492795822413, -14, -2.191783086434616, -2.217508210196444, -14, -14, -2.1770676002613576, -2.1796924317091326, -14, -2.168111693773582, -2.1756310612073206, -2.1674083380231877] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1303  total reward: -4099.545763651971
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.415529681269691, -2.170756707262804, -1.893909148905813, -1.7690204561864824, -2.2236902633155737, -1.7494440536918674, -1.8560525134114527, -1.9408190246529202, -14, -1.809814387628802, -1.8844724561129966, -14, -1.7494440536918678, -1.7562779606672374, -1.74258446216606, -14, -1.7694493827807254, -1.8966397906742696, -1.7607100839443106] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1304  total reward: -4103.047842340489
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4893274714382647, -1.9735147651396183, -1.8478447199595778, -1.8653327827696615, -2.050304946112079, -1.7794517055650112, -1.7940702631548078, -14, -14, -1.8154443917444179, -1.896410093459145, -14, -1.9248604708953934, -1.7813527018749624, -1.7692153590331843, -14, -1.7717647786453437, -14, -1.7594942263522062] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1305  total reward: -4107.474974655021
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3426099769870503, -2.920233140060863, -2.663521346527863, -2.7033158597251936, -2.5624846225877427, -2.752412583154099, -2.6758968039032687, -14, -14, -2.7418880813189976, -2.84574498162116, -14, -2.856428285905014, -2.5798315995355674, -2.4858746406463066, -14, -2.682787519029024, -14, -2.667638088178723] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1306  total reward: -4111.739829154209
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5680297260693394, -2.0807016812849497, -1.8886333652357699, -1.8543855036335115, -2.129250723407533, -1.7915227106846352, -1.8134628883043475, -1.972960328598323, -14, -1.8174092644812196, -1.8701336982497219, -14, -1.9338405881684109, -1.7917801242008973, -1.7715123945182816, -14, -1.783413496725428, -1.8263168427270413, -1.778979858542141] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1307  total reward: -4114.947378652956
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0019760506377726, -1.6053275204032937, -1.5040269009773368, -1.5131096340317534, -1.6375849489938439, -1.4659213961360353, -1.4501027015727113, -14, -14, -1.4887113521908937, -1.5716276615927538, -14, -1.5520280429601572, -1.452627069732896, -1.4320356364979479, -14, -1.4497746095866026, -14, -1.4360371042291609] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1308  total reward: -4117.6515203439885
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7599319124212502, -1.4894135992909023, -1.3437114772918466, -1.3023409774526158, -1.4823448763516303, -1.2713421408472096, -1.306671164488177, -1.4673349591392797, -14, -1.3057472783509665, -1.3408160388368608, -14, -1.4010691445433183, -1.2820443227009082, -1.2803411798034734, -14, -1.2738437620223642, -1.3029806127972503, -1.2721060545343306] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1309  total reward: -4120.2995476984
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9444972786322527, -1.5916835575112867, -1.4610029450105397, -1.4316615717811358, -1.6701546320789815, -1.362084650504901, -1.3759903920173446, -1.480186389751038, -14, -1.407445945985308, -1.4322586928733019, -14, -14, -1.3781077616059427, -1.410850438085438, -14, -1.3785665172093355, -1.3933890422850728, -1.376685213563762] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1310  total reward: -4122.512938884146
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4918561824199381, -1.5079033425823514, -1.1656177917243182, -0.9718313670760305, -0.9020901536535206, -0.8790684456173942, -1.0032889153141793, -0.8554089187382907, -0.8700561360688912, -0.9623236137478225, -14, -0.8697380632255735, -0.8945839838231614, -14, -0.9314032311132217, -0.8578190756091928, -0.8565442667772694, -14, -0.8534746827051171, -0.8774097380974084, -0.8513065352418608] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1311  total reward: -4124.209282375672
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.491890574520512, -1.4971650734811313, -1.1495217403024662, -0.9719815340963632, -0.8974851133614985, -0.867142346417028, -1.0080645452600137, -0.8427172289481183, -0.8682024232914226, -0.9516033293499198, -14, -0.8638300940766562, -0.889265550330782, -14, -0.9246119614225166, -0.8504205636358718, -0.8408849244587401, -14, -0.8471556478908213, -0.8714187143857232, -0.8450369562835915] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1312  total reward: -4125.805478052795
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3218568896069016, -1.3736504394764788, -1.0376826275477598, -0.8426254989077114, -0.7953352781474817, -0.7917328896768091, -0.8895220612481058, -0.7785040241718927, -0.7599127752699985, -14, -14, -0.7785113112222798, -0.8168200382172328, -14, -0.8188423433760426, -0.7657558962545327, -0.7574551462465076, -14, -0.7619664687126677, -14, -0.7553107526650308] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1313  total reward: -4127.069394753033
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8391623714233214, -0.9204703428487959, -0.6993766554650157, -0.5634003690694875, -0.5306963575941948, -0.5359007831705174, -0.5700106542458807, -0.531127744502264, -0.5101502760543609, -14, -14, -0.5274154699359537, -0.5568527692632005, -14, -0.5549381606640613, -0.5137845006286765, -0.5042049086561106, -14, -0.5134543262643658, -14, -0.5086059475732362] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1314  total reward: -4127.925152940121
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3559641860689893, -0.35345221217646955, -0.4571692566685055, -0.4031635743086732, -0.35057684177044873, -0.3556799361606408, -0.3546352447058648, -0.4613894460398673, -0.35057247765203237, -0.36823482009929376, -14, -0.36558762433673153, -0.3835961792535901, -14, -0.47148805418460377, -0.3530993601027461, -0.3531571313596915, -14, -0.35379459448885264, -0.36938603075304743, -0.35155327843217254] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1315  total reward: -4128.909193170617
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0544076744518978, -1.1145939172235089, -0.8867040634653972, -0.7276993372025096, -0.6675666917758354, -0.6580087568568681, -0.7299482846917288, -0.6231414857406935, -0.6156244805823182, -0.7626437291409699, -14, -0.6490333811227806, -0.6763213615538405, -14, -0.9400539084053174, -0.6363440329895997, -0.6241283445564326, -14, -0.6361769015609523, -0.6775923937923389, -0.6334677528440303] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1316  total reward: -4130.370886110022
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4380150926572712, -1.4740169592817625, -1.2064025708096662, -0.9862416812067784, -0.8975051293602758, -0.8789256054161133, -1.0088017875449358, -0.8530951865688922, -0.8628520689102799, -0.931228096544701, -14, -0.8670562182162574, -0.895331628656922, -14, -0.9242497454183582, -0.8513184888771664, -0.8474063150072205, -14, -0.8486147277051926, -0.8749487037605349, -0.8460684588223699] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1317  total reward: -4132.3625521087
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9257847971084, -1.9896563784837633, -1.570258506554402, -1.3051246294255792, -1.208250009463745, -1.1853805598855174, -1.327699914760081, -1.1627082099051886, -1.171485759696419, -1.3021918130674859, -14, -1.1704830435491302, -1.2030019480838243, -14, -1.286254457839801, -1.1547450376265058, -1.1508976442156964, -14, -1.1483537984915473, -1.1699324781228255, -1.1455975398545188] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1318  total reward: -4134.737062209946
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6954972280435572, -1.4240290406455343, -1.3006544138217342, -1.2635704001453414, -1.448305345542723, -1.2329486726488321, -1.2603506131002138, -1.3718355069321022, -14, -1.260239019713655, -1.3007905995348368, -14, -1.3574429602868638, -1.2381085473080868, -1.231307382651335, -14, -1.2324082799844667, -1.2705546597074688, -1.2289125613927165] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1319  total reward: -4137.310682042746
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.918605566294064, -1.565625695806649, -1.4210965776912856, -1.3983019507554106, -1.5779439666715198, -1.3554555876145136, -1.3755628337210293, -1.5117698105178534, -14, -1.3799087150988718, -1.4224470258344288, -14, -1.4876435789083429, -1.3543168251276763, -1.3537459846675235, -14, -1.3479100637065557, -1.385316077248659, -1.3447072714070367] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1320  total reward: -4140.403733054467
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.564684463692501, -2.0042643252571497, -1.8488763053017785, -1.8610790244210726, -2.0553698850321505, -1.7549152167762845, -1.789419385357239, -1.9725055926391561, -14, -1.7868449008073397, -1.8376627983869886, -14, -1.9187261692741293, -1.7606089607621802, -1.74690205098484, -14, -1.7525932550381516, -1.791073169330354, -1.7483437403136997] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1321  total reward: -4143.760434323993
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.271328770164837, -1.7691179450957302, -1.682661712660127, -1.7332561168208813, -1.8297314358353025, -1.6857864390864292, -1.6144888784613056, -14, -14, -1.6699130694873159, -1.7622488898900794, -14, -1.7628536526957308, -1.6288279016820884, -1.6025583118703461, -14, -1.6247165715569858, -14, -1.6097992185413512] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1322  total reward: -4146.990864943818
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.3627451963958843, -1.8599588093204216, -1.716085217307034, -1.7256659596856965, -1.874025150068326, -1.6361813385942032, -1.6628146774674002, -1.8870571322798757, -14, -1.6602101426045923, -1.6988033708543602, -14, -1.7822291837995792, -1.6404794837899184, -1.6401779609685516, -14, -1.630523883702125, -1.6521679641863378, -1.6278723079555166] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1323  total reward: -4149.9713532687965
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8490674574138117, -1.5580556295083956, -1.4376529199021217, -1.3898124437452517, -1.6220950729335968, -1.3647112930739693, -1.3788280661246424, -1.4915553340335268, -14, -1.3839188628543915, -1.425215970999403, -14, -1.4762951753904439, -1.3617725318612341, -1.3494379629573896, -14, -1.355890989619502, -1.394289631535835, -1.3526160170213835] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1324  total reward: -4152.9824978876695
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.341144607686925, -2.081556258414546, -1.7862261085223388, -1.672660404769816, -14, -1.6680445559422137, -1.7630958144580644, -14, -14, -1.703540287563794, -1.7673275633956513, -14, -1.6680445559422141, -1.6670080833205647, -1.677414682328401, -14, -1.671933170349701, -14, -1.6617066559157287] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1325  total reward: -4155.81048134851
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8126847517525084, -2.151897314099966, -1.6221481719838267, -1.3252381374203264, -1.2090914110144495, -1.2144093869287713, -1.2794765504230978, -1.2014853177142029, -1.1751719704004566, -14, -14, -1.2132822931042646, -1.2827416877409776, -14, -1.2713858424988107, -1.1750781301830546, -1.150112906425742, -14, -1.1770469289396042, -14, -1.1662768049246723] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1326  total reward: -4158.0606484309765
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9219422979440188, -1.9596339666217095, -1.4877394044926395, -1.28042819971544, -1.1688009254208829, -1.1206356451803223, -1.316029565160183, -1.1020840849308229, -1.1262516400004388, -1.250563733785604, -14, -1.1260568629466232, -1.1599478657713334, -14, -1.2020531091762752, -1.1080680976178863, -1.1005797786753277, -14, -1.1027690566925028, -1.1314752862266864, -1.1000541760413254] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1327  total reward: -4160.353332451032
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6517655470712072, -1.3911765738557502, -1.2586139418488005, -1.2230590205184677, -1.3795244381202219, -1.1851513440910335, -1.2297574336999502, -1.4045397650499374, -14, -1.2186781782965956, -1.2527381068166314, -14, -1.3114840570533073, -1.2015587018692795, -1.1974169852571512, -14, -1.1957541862131176, -1.214291179604471, -1.1926298440141614] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1328  total reward: -4163.520224816371
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6667963541030657, -2.2906208701307604, -2.0484334324512847, -2.017400851663677, -2.1272690220659185, -1.9591973240348375, -1.9934192510452955, -2.759536001147976, -14, -1.9942242582417546, -1.9955513223425445, -14, -14, -1.9589943197016795, -2.1870106902339588, -14, -1.9812597235191962, -1.9937669611780227, -1.9817410212486866] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1329  total reward: -4167.109470882161
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.306865547795866, -1.899616308520937, -1.7367794281132805, -1.6883334484344703, -1.9796128701275673, -1.6296077042141601, -1.6288229791759417, -1.7312610279735439, -1.67801890360046, -1.6629281419942312, -1.6863000163868984, -14, -14, -1.6283151158058575, -1.6588380746216935, -1.6520253356468038, -1.6338103938563877, -1.648546304184311, -1.6302517460881565] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1330  total reward: -4170.584923848486
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.253344450666502, -1.8824158858175188, -1.9451815550119609, -1.9787687847872668, -14, -1.7880222273002333, -1.8515487132204647, -1.8655069026690567, -14, -1.8764492899519931, -1.9113833203554997, -14, -14, -1.854270255684277, -1.8633509066804648, -14, -1.8499219302317849, -1.8820226390018453, -1.8471378505186913] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1331  total reward: -4173.416240077988
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7352322628595698, -1.8163599837588276, -1.4843011625571372, -1.205726125831654, -1.1017790174346846, -1.0880071721137559, -1.2179531935528134, -1.0609846454704526, -1.0612588685836304, -1.1533273878606365, -14, -1.0688681632508474, -1.104995283262713, -14, -1.1515659711550401, -1.0519145691385385, -1.0493460127233003, -14, -1.0473302456130513, -1.062398709412915, -1.043294002201679] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1332  total reward: -4175.798119829387
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8984367322807316, -1.5080134058247965, -1.416688189787322, -1.4178559207894685, -1.5765323151158563, -1.359786044027542, -1.3604831100673038, -1.4931006930487492, -14, -1.3673664049581495, -1.4062976210955458, -14, -1.466624168705885, -1.3493777092957844, -1.3478050121020224, -14, -1.342043077444155, -1.3714519330760027, -1.3385857491981232] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1333  total reward: -4178.3414292068655
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.69265167952801, -1.377821608363351, -1.274908560958528, -1.2572507320244772, -1.4174348208355603, -1.2101165533994431, -1.23297676661477, -1.347428181770203, -14, -1.2326743591451155, -1.270734152368433, -14, -1.3241170135393654, -1.213751583731932, -1.2090948011900085, -14, -1.2082597794753214, -1.2438899547973266, -1.2047236282796698] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1334  total reward: -4183.733538029113
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1335  total reward: -4197.733538029113
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.95171200229325, -1.5599643544854487, -1.2884059034012647, -1.4275441963639774, -1.52145107269844, -1.3712054802392684, -1.3843585748282734, -1.4784273457413144, -1.4502046147804273, -1.396899771529726, -1.4362993500826338, -14, -1.456835142475834, -1.3520387518429662, -1.3667752224308183, -1.4059697956216188, -1.3699786419651099, -1.403300104506956, -1.364503950652413] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1336  total reward: -4200.290855779732
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.838542429278459, -1.4443190668202275, -1.3411666943666865, -1.348947484263067, -1.4616602169561694, -1.2691235922890542, -1.2978084153513867, -1.3800443558087765, -1.3308504151122225, -1.2959199901010166, -1.322838480994431, -14, -1.3998959176655463, -1.2607152888185238, -1.2767427842558945, -1.2973643484492319, -1.2717968215177065, -1.3041737602874401, -1.2689118472177083] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1337  total reward: -4202.615393268554
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.823566760988217, -1.9072712958493505, -1.4912265897624142, -1.2376722937137317, -1.1271497959350922, -1.0977046929944303, -1.2531024274364446, -1.0659758254097613, -1.086823482560045, -1.2348129073078504, -14, -1.0858392711501927, -1.1170118033828196, -14, -1.1551706793828342, -1.0725666311666293, -1.0716813591255663, -14, -1.0669480781873903, -1.0840436925939516, -1.0638222000029274] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1338  total reward: -4204.652391887219
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6605516533689522, -1.6604690602126109, -1.3733532161027566, -1.1185294343132206, -1.0314031636734957, -1.0151910273329086, -1.1596180599166432, -0.9912707495100549, -0.9902039874107941, -1.0674882867750648, -14, -0.9932176983234626, -1.0231261586426832, -14, -1.0746290689030398, -0.9806103836152174, -0.9703603028293207, -14, -0.976096505109776, -1.0021934656555795, -0.9731764186627101] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1339  total reward: -4206.6373052539
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6110134180096811, -1.8909147915610327, -1.3884467786754278, -1.167800726255102, -1.0566036180784124, -1.0419980472319814, -1.1393374728583812, -1.0387783412155576, -1.026675540822619, -14, -14, -1.0554556014980108, -1.1139126788944893, -14, -1.11136545465027, -1.0253553287542654, -1.009808822775506, -14, -1.0232904438750328, -14, -1.0145530638515552] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1340  total reward: -4209.122871045415
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0551482208265757, -1.712709346980457, -1.5624712561864051, -1.5217596355903755, -1.7426948158699993, -1.4808261877747173, -1.5138484404139287, -1.6487511184009138, -14, -1.5104255670918463, -1.5582328343700502, -14, -1.6313466239700223, -1.485422756733373, -1.4763912960240955, -14, -1.4801771033245212, -1.5290488384799195, -1.4757569687399075] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1341  total reward: -4212.825439186256
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.264422164961719, -2.559031365302657, -2.368231813962376, -2.366554889496001, -14, -2.2380193161781223, -2.269500224024479, -2.4137789838487524, -14, -2.276906847277478, -2.35069857412115, -14, -2.4047616575813473, -2.237400991303863, -2.2160442387516297, -14, -2.2338401875389557, -2.3229962256204915, -2.2268111721008568] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1342  total reward: -4217.25006400209
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.8830599336211433, -2.5010874307915105, -2.3009799090546443, -2.246323873203204, -2.465405965425132, -2.2477310374449377, -2.2506154898869055, -14, -14, -2.291148295100624, -2.417632572519302, -14, -2.446002424492193, -2.2318977230845785, -2.201962393175717, -14, -2.2289575566861473, -14, -2.2085805770826843] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1343  total reward: -4221.95627810095
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.5135053861848955, -2.8101794204516954, -2.6332622625648447, -2.642629898477413, -14, -2.504317448539482, -2.577176408937761, -2.972600532280298, -14, -2.557776448749399, -2.6182771219695793, -14, -2.787069638328959, -2.522600310639526, -2.5371918200481502, -14, -2.5082022072498726, -2.54959649476274, -2.5042517056834077] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1344  total reward: -4228.459790552931
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1345  total reward: -4242.459790552931
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -3.8111656763358392, -3.151609713463446, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1346  total reward: -4248.405912781725
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2826330743033574, -2.9702515315406024, -2.9048994041711613, -14, -2.8149669891510327, -2.8346115832206062, -2.9927265035991355, -2.925113845120855, -2.8562710639729274, -2.9175626439449873, -14, -3.007484750623787, -2.7728298661760413, -2.8046545777361507, -2.8598472631226195, -2.8011791179299457, -2.8523044544606244, -2.7945125153309807] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1347  total reward: -4254.012048393314
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.1923145707104448, -14, -14, -14, -2.8680613337970313, -2.876891587615703, -3.121409008092842, -14, -2.8890461704414, -2.963984281008404, -14, -3.0655500823206405, -2.8540338372045206, -2.8311268759706367, -14, -2.839025696251406, -2.9102560553974417, -2.8333057454130066] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1348  total reward: -4259.23574351633
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.293155690025761, -2.63779789206338, -2.4945561528355427, -2.532125027892693, -2.674409858148912, -2.5040109339792447, -2.4013590679951333, -14, -14, -2.4802536038922964, -2.6157463492197035, -14, -2.6288026216394416, -2.4170850475801573, -2.373765718229183, -14, -2.4145938577981494, -14, -2.3925682470457157] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1349  total reward: -4264.226183021049
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -2.9116617638286533, -2.7735420623984512, -14, -14, -2.6393952581933338, -2.6539830651020853, -2.7990932571004428, -14, -2.6727102604315105, -2.7492862038840498, -14, -2.7964474807337165, -2.6297029795320204, -2.6029556502047804, -14, -2.6230157330102863, -2.7002184728133036, -2.6166737864891414] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1350  total reward: -4269.147002233127
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3429871032516707, -2.6049899980646507, -2.4378196013489624, -2.4782720112789764, -14, -2.367390473253752, -2.335606769370636, -14, -14, -2.387776787986029, -2.501788955287145, -14, -2.4879077400683705, -2.34802788623656, -2.322886333535083, -14, -2.3374322554326707, -14, -2.3178635618734704] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1351  total reward: -4273.845279631991
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.2832354078917976, -2.7062680211467325, -2.4954829694487457, -2.4695767920232328, -14, -2.4366158062806735, -2.4114307266476485, -14, -14, -2.44653578216151, -2.54949565547556, -14, -2.6160502650602617, -2.410981238953788, -2.389272462973572, -14, -2.397283846506813, -14, -2.3804138369903813] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1352  total reward: -4278.5974321510685
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.274570336407773, -2.685848044394504, -2.4671048388449988, -2.469897264709153, -2.659781890628463, -2.481553580074593, -2.388384327465, -14, -14, -2.464774612011303, -2.601225482163505, -14, -2.6477069660512154, -2.398530096083511, -2.360555890268889, -14, -2.3927247484207608, -14, -2.3717386820869386] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1353  total reward: -4283.281950021074
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.252807145772821, -2.6463903153269004, -2.453600546844804, -2.42677402634625, -14, -2.313363890267488, -2.3976099193438714, -2.655885186396314, -14, -2.3793169576587303, -2.4568351374716273, -14, -2.5732369915173168, -2.3388188843275506, -2.3382508634327834, -14, -2.3321784265493326, -2.40009577946445, -2.323961979736914] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1354  total reward: -4287.954195148484
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3558141947188584, -2.7140607525940554, -2.506190246538487, -2.4703311386321936, -14, -2.2986247162762234, -2.3531763881085186, -2.4978637529515653, -14, -2.4034508828944645, -2.4410043617583255, -14, -14, -2.3643208405985474, -2.4101240208328956, -14, -2.3606018494931695, -2.3749614221586626, -2.3588812371428105] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1355  total reward: -4292.440049168949
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.14830206673846, -2.5184622505629846, -2.323504712117509, -2.297842495739476, -14, -2.1744863840918085, -2.243066918829915, -2.448799508574044, -14, -2.2321201246113063, -2.2950110486067787, -14, -2.3562687771769015, -2.199309286790861, -2.1777575229379864, -14, -2.192664504163288, -2.2633818102438785, -2.1872293041888526] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1356  total reward: -4296.40489625214
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.4207189306508745, -2.0373489945134122, -1.8968592024001094, -1.842176267999463, -2.126025385822834, -1.7848835753250092, -1.8024146341591125, -2.0039312804837457, -14, -1.8279158622463063, -1.8571037669697563, -14, -14, -1.7891713840584633, -1.8564575116348772, -14, -1.7931313934050206, -1.807021476981648, -1.7903606990986243] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1357  total reward: -4299.782229141223
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.122918594758235, -1.8723871891202162, -1.68736700687001, -1.609139558398776, -1.8782202061231883, -1.5887302295651493, -1.6356560753188316, -1.8230385884756586, -14, -1.6346978358133801, -1.6846963776268815, -14, -1.744633168133006, -1.6051008755130856, -1.5969157303971921, -14, -1.5961524174621717, -1.6307049681309347, -1.5924493137581142] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1358  total reward: -4303.248763503328
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6189620251177494, -2.1561590291447317, -1.9942167661426355, -1.948895640493166, -2.2733428123658124, -1.870071530128634, -1.8843693961004473, -2.0326861155782305, -14, -1.9163122344816879, -1.9534478349210633, -14, -14, -1.8782645722413938, -1.9238413153401377, -14, -1.882187995072013, -1.9075327757788691, -1.8778041325395423] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1359  total reward: -4307.334979912436
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -2.615879207510757, -2.2815408478204753, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1360  total reward: -4311.12037509448
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -1.3001155783254883, -1.5902442297959725, -1.5281119077734973, -2.0367359798003624, -1.5168652468365942, -1.5245465371193239, -1.6985115794811703, -14, -1.5373121850751863, -1.5931113138971973, -14, -1.589253379295725, -1.5166131595478665, -1.475213262334533, -14, -1.508592875661981, -1.5616552868729126, -1.503854334222564] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1361  total reward: -4313.617759961114
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.6926694453836066, -1.3756916192519113, -1.2746729050001218, -1.249705846435597, -1.452361421330665, -1.195266429088365, -1.225522343565343, -1.29813020688109, -14, -1.226110115042232, -1.267153128738985, -14, -1.294294097971755, -1.2021396537081561, -1.1874424976114384, -14, -1.2010909945742787, -1.2449446178789327, -1.197269288307912] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1362  total reward: -4315.901598944648
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7671739045900134, -2.009008449611147, -1.4600030610503998, -1.2285850852351987, -1.140870540456997, -1.1296627154486643, -1.2169561007830256, -1.136799859204852, -1.1057065959317143, -14, -14, -1.1355975354153436, -1.198538347258863, -14, -1.2130079316534255, -1.1064072840578596, -1.0886128487073998, -14, -1.1070342749217095, -14, -1.0963964859234208] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1363  total reward: -4318.259648768524
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8060145034912707, -1.467595909336939, -1.3460664096510477, -1.3239813242718717, -1.5124699999106843, -1.2650602635011454, -1.3053254088668442, -1.4143796813235399, -14, -1.3037238969221778, -1.3484995896237835, -14, -1.39094092396833, -1.2770140018557035, -1.2661395086058564, -14, -1.2733933453689257, -1.3141796817924136, -1.2694369751685222] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1364  total reward: -4321.126059764076
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.1346297176427007, -1.8522757603568873, -1.6960862658063063, -1.6273082051963368, -1.9023259879052967, -1.6121843926497592, -1.6390934885666215, -1.80456298282173, -14, -1.6382108202623837, -1.6690608055622826, -14, -14, -1.5995562201573565, -1.6557715601341934, -14, -1.6054264829045468, -1.630889878990025, -1.6013507320507698] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1365  total reward: -4326.384888863978
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.65234221212542, -3.8256432911855467, -3.6283698438625582, -14, -14, -3.7125050362078573, -3.7122330239445334, -3.7435586531348344, -14, -14, -3.6541989478394243, -3.692048300161181, -3.6775074052579395, -3.6691632598886526, -3.6871361883515408, -3.6592728797444276] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1366  total reward: -4332.235939527354
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.057069501584136, -2.575172945082948, -2.3464810373569622, -2.2818375249110328, -2.538936381093525, -2.2240615251258213, -2.2751660108818137, -2.4720288617428308, -2.3224472229091475, -2.280741445635854, -2.3343191200609223, -14, -2.4646655128637436, -2.204472331428366, -2.2570178342468417, -2.2624150441830673, -2.2293088864129063, -2.2643264886062715, -2.222680819514079] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1367  total reward: -4337.427609355584
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.47978614531201, -14, -3.0749209167647895, -14, -3.0096529234664757, -3.0581730325683822, -3.337674587629087, -14, -3.0535008529567302, -3.1471644395125766, -14, -3.307139469990173, -3.0085134467334447, -2.987331067089232, -14, -2.9958932643612615, -3.0904460310000257, -2.9871974968005217] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1368  total reward: -4343.837741539101
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.454719820057745, -3.4845546709248802, -3.805731405264136, -14, -3.4932018971723022, -3.5956231484477787, -14, -3.7175584941814073, -3.4476465383046446, -3.4235012360303525, -14, -3.4324490198071724, -3.5331029678748496, -3.422934686717815] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1369  total reward: -4350.275436435654
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -2.9728849740362757, -3.1173175821954127, -3.414699290169301, -14, -3.08861987137402, -3.1806260149341887, -14, -3.2602468460490557, -3.0331408325827796, -3.0048397889711698, -14, -3.021953072289554, -3.117935626801565, -3.014760209834422] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1370  total reward: -4356.6275130691965
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.373459120309025, -3.4014676955434213, -14, -14, -3.4502631390584706, -14, -14, -14, -3.382328866466217, -3.4520539100637877, -14, -3.386914711020618, -14, -3.3791916595064593] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1371  total reward: -4364.8250721622035
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1372  total reward: -4378.8250721622035
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -4.557512146845715, -3.6671039855972136, -3.027699340986442, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1373  total reward: -4384.300277850506
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.545931211037019, -2.7751700548169635, -2.5921591688609205, -2.6085040520181884, -14, -2.457819453144772, -2.490789037568617, -2.641828757144533, -2.55937099151153, -2.5015557991844024, -2.5599676078111355, -14, -2.6623100446479566, -2.4291719357998462, -2.4587453059828763, -2.4996169458236257, -2.455501687292318, -2.4889368363715807, -2.447506347315527] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1374  total reward: -4388.98006589829
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.0891430601840164, -2.6128152446590254, -2.3796227344004537, -2.305554845632051, -14, -2.2325300590632553, -2.3201518564103623, -2.6672327775152835, -14, -2.3047913589407534, -2.3712091032373896, -14, -2.4583408725774554, -2.267723252946636, -2.270767003390312, -14, -2.256118170061267, -2.2983388907122886, -2.250616111984708] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1375  total reward: -4394.040596906407
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2191740256844366, -14, -2.992794542940428, -14, -2.81821634303227, -2.842877149332384, -3.041690967806816, -14, -2.8794944538364318, -2.937341520188172, -14, -14, -2.8312389242907297, -2.8731947551093504, -14, -2.8363099908087044, -2.879371009866477, -2.8280009490531097] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1376  total reward: -4400.904456587002
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 0
Action chosen: switching off line 0
  Simulating cascading failure
    depth 0: 2 overflowed lines
timestep 1377  total reward: -4414.904456587002
Game over! info: Cascading failure of depth 1 lead to a non-connexe grid
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -4.711507434743534, -3.7540300791938197, -3.0593080537456587, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1378  total reward: -4420.565157067824
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.051107204852441, -2.759509150626535, -2.709777323203346, -14, -2.577946342152037, -2.6626219059865894, -2.8428747626627047, -2.736382441298256, -2.6591040033765387, -2.724146377423819, -14, -2.8127992436815634, -2.583216011896902, -2.613373214369431, -2.6702682334906127, -2.610346960949805, -2.6655987529168317, -2.601392427076469] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1379  total reward: -4425.873909296556
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
rewards [-14, -14, -3.223194819459045, -2.7967684347663946, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1380  total reward: -4432.368149069252
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 3 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 8 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 9 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 10 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 11 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 12 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 16 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 17 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 18 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 19 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with no action
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
rewards [-14, -14, -14, -3.214624610864231, -3.8048966867316625, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14, -14] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1381  total reward: -4438.022569526736
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.3643699660379975, -2.7939307465860166, -2.591333860266883, -2.5240273905770247, -14, -2.436384867567477, -2.441914946583913, -2.6127960937129777, -2.5166870081538697, -2.486560073018403, -2.5204808981129463, -14, -14, -2.440849502390314, -2.4982778314336986, -2.4667236343476415, -2.445512386775165, -2.4686033406772, -2.4397958466200693] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1382  total reward: -4442.544443776879
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.81622827309636, -2.43472754900992, -2.216204656439382, -2.120239942992247, -2.4405031243282562, -2.065869498970418, -2.137107554821555, -2.3032642349764556, -2.1901281927437535, -2.130822480109136, -2.1790205856559997, -14, -2.264248418849895, -2.070758325847333, -2.096305439460487, -2.134422969549064, -2.0914042998123814, -2.137577450421597, -2.0854893825760326] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1383  total reward: -4446.167235941186
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.127834352659249, -1.8144248093641309, -1.6534610237378145, -1.5904810697819665, -1.8584727306919835, -1.5817074838414562, -1.5938976716371343, -1.6868189725105396, -1.620316446664632, -1.5985441097974706, -1.6257650451946029, -14, -14, -1.5567905141303207, -1.5888989786782066, -1.5882110637342626, -1.5610799491787268, -1.5899462708670535, -1.5569226653360082] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1384  total reward: -4449.11655144584
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8942592622639802, -1.6020673317542213, -1.4730307174556647, -1.4288301073807204, -1.6490966530340194, -1.3856426784589582, -1.4014933758458348, -1.5613153061226372, -14, -1.4206563178829332, -1.4409754050852461, -14, -14, -1.391457780209582, -1.4401005826536784, -14, -1.3941192484764315, -1.4047064290917781, -1.392524990523343] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1385  total reward: -4451.598321011954
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8572284128781509, -1.9129822744045528, -1.5415060507256104, -1.275544468440217, -1.161621498868207, -1.1331900877971783, -1.3003767379314484, -1.0937398894477262, -1.1271187073394477, -1.22409471372707, -14, -1.1212299255693903, -1.154993586495661, -14, -1.2049159210844531, -1.103472802447198, -1.0907389744059397, -14, -1.0989327706738987, -1.1353904326851303, -1.0961268876550945] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1386  total reward: -4453.792259142586
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8960522622685199, -2.0469992729066817, -1.4692104976684432, -1.2464769109466376, -1.1594651651188728, -1.131743717681917, -1.2853363864253402, -1.1200701081014983, -1.1206291381815432, -14, -14, -1.1427854045233143, -1.2015243915257596, -14, -1.203142449607518, -1.117264281547639, -1.106393216415174, -14, -1.1123478275292178, -14, -1.103199156225971] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1387  total reward: -4456.1746663535605
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.769344459905609, -1.4338096167626921, -1.339078592832558, -1.3403861445379845, -1.4579220737421692, -1.3129042338360244, -1.2889061085787676, -14, -14, -1.325779305477572, -1.3945922769742014, -14, -1.3849586441377597, -1.2936047496717322, -1.2742971233085987, -14, -1.289877149339765, -14, -1.2792080547486178] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1388  total reward: -4459.221906599987
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.46208539793772, -2.0796217970210646, -1.8790476309889248, -1.8157499427174295, -2.092120143598862, -1.7603553370847027, -1.8237776963947625, -2.047947353485371, -14, -1.8173714618708403, -1.8766451019505268, -14, -1.9260774232680056, -1.7851266995544717, -1.7845221990035833, -14, -1.778707379400587, -1.822629728254153, -1.7729431231181625] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1389  total reward: -4463.167774776709
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1441254623864316, -2.5708972392704896, -2.3187306268280627, -2.26893923812189, -14, -2.151786134340531, -2.179666631268983, -2.3232990917549263, -14, -2.2254802540119427, -2.265256332507819, -14, -14, -2.1886317176058045, -2.2373892020204993, -14, -2.189357240121964, -2.2184795893346694, -2.1855128396369725] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1390  total reward: -4468.062514967227
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.182494194151104, -14, -2.8386856788256156, -14, -2.7102066881136886, -2.8306727301782892, -3.1292002550231737, -14, -2.809715268392438, -2.8906845654878333, -14, -2.9662997819086896, -2.759683379589162, -2.744227695432828, -14, -2.74885117935709, -2.838238196622616, -2.742954056177434] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1391  total reward: -4473.906662643751
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.0888929827416143, -3.12742049309976, -3.42901215836454, -14, -3.190857428959563, -3.2358488245046213, -14, -14, -3.132280947679057, -3.234315349587157, -14, -3.136638299556067, -3.153300995146393, -3.1339409884102674] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1392  total reward: -4479.847103239446
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 4 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.3153149455387956, -14, -2.9080516629943562, -14, -2.8606983459250337, -2.9275897221789573, -3.395126410011088, -14, -2.9195118422126454, -3.0043312969081604, -14, -3.1724801874265856, -2.8744670964600387, -2.913078745121511, -14, -2.8595019543355575, -2.898829252038553, -2.851547612953775] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1393  total reward: -4485.43027180114
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.2311315739905067, -2.88771623479441, -2.762249410441616, -14, -2.7058221495436787, -2.8339760038842163, -3.11081947099319, -14, -2.818995056191983, -2.9341429853917775, -14, -3.0406019492192073, -2.7490448104683476, -2.756038082393521, -14, -2.7436112772305012, -2.8550299348550383, -2.731620948741214] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1394  total reward: -4491.2736648766195
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 6 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.125659848897373, -3.1450090157586352, -3.423053744823022, -14, -3.195218041480806, -3.242100235616103, -14, -14, -3.1389334483758473, -3.184532243275937, -14, -3.1409458145181395, -3.178660363103787, -3.137570925935034] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1395  total reward: -4497.379116659808
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.1002921006254778, -14, -3.0274314133334914, -3.0283606894936783, -3.321513339859683, -14, -3.0394412172104404, -3.109461248375422, -14, -3.2630698504530793, -3.0031388110468145, -2.975771352623498, -14, -2.9833960969206648, -3.0394796257511594, -2.979791934291256] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1396  total reward: -4503.162347739658
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.1535836666411172, -2.934801473612244, -2.9734412997698825, -14, -2.907376939668771, -2.8341332854872006, -14, -14, -2.899000385661893, -3.0313983936019095, -14, -3.112023293403153, -2.8428479037246874, -2.8120880489061113, -14, -2.8275131164857052, -14, -2.8074597272262656] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1397  total reward: -4508.009367300863
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.6887448188771597, -2.2658526515904853, -2.132471793993151, -2.102843965142075, -2.3083461835085264, -2.1147175668991895, -2.053792317563213, -14, -14, -2.11964077546579, -2.2416763655251124, -14, -2.2422341307466387, -2.0627803248104404, -2.0293758987020314, -14, -2.059112987977286, -14, -2.039559833979275] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1398  total reward: -4512.33211785717
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.1827705580725305, -2.5668488223617585, -2.4283374528437074, -2.4126605995663706, -14, -2.295018401565183, -2.3528325789956916, -2.593063385806477, -14, -2.3463761973787296, -2.407309529497828, -14, -2.5210298449352404, -2.3080123841525357, -2.2872128066495527, -14, -2.2968737157369814, -2.347905570712413, -2.293374657603519] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1399  total reward: -4516.9154984946235
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.192092039940617, -2.5687564759772488, -2.386643162867431, -2.4156767811007227, -2.537186560640919, -2.371833888013205, -2.3132898870531022, -14, -14, -2.394665461624822, -2.539364587077516, -14, -2.513135754840953, -2.316335445396887, -2.2712340075804396, -14, -2.318462369765808, -14, -2.296167830804471] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1400  total reward: -4522.34101802835
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -14, -14, -3.2288919374123086, -3.2099592001165997, -3.4429489832674807, -14, -3.2167651154695602, -3.3062371108302355, -14, -3.522133298566051, -3.1765087725476575, -3.1451470603691165, -14, -3.162284890761352, -3.2445882703741757, -3.154285526146832] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1401  total reward: -4528.460140640331
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -3.3312419839730443, -14, -3.085308579509557, -14, -3.0867738443995236, -2.9934189475330077, -14, -14, -3.1064680626784287, -3.2967481361531057, -14, -3.2689809536935917, -2.9999827605091363, -2.9341905159970194, -14, -3.0025711203067975, -14, -2.9739755516118223] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1402  total reward: -4534.919115706754
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.6045527186866497, -14, -3.5440748877041326, -3.618624313540783, -5.238466457684183, -14, -3.5522767390472008, -3.5691739338517494, -14, -3.97232378958476, -3.5312571187783353, -3.7299655076603346, -14, -3.523611017762612, -3.516072488448825, -3.524784550425991] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1403  total reward: -4541.179150206319
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -2.7519798068213235, -14, -2.766056452977406, -3.0974129742860823, -14, -14, -2.7849608859394395, -2.811404018307734, -14, -2.766056452977406, -2.6826552847692957, -14, -14, -2.7444382375613197, -2.5815165719395536, -2.7439620111155127] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1404  total reward: -4546.160433525472
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -3.4377777066787907, -2.7138167940779283, -2.5371942416531668, -2.5478552201394318, -14, -2.4248099815195365, -2.449318447540381, -2.7043054472620067, -14, -2.4526575040970258, -2.513292257721185, -14, -2.645909583381102, -2.4172360198741405, -2.3971160819193975, -14, -2.403099114296746, -2.445513878973755, -2.399766747214132] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1405  total reward: -4551.870755639157
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 2 overflowed lines
 Simulation with line 3 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 3 overflowed lines
 Simulation with line 4 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 1 overflowed lines
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -14, -14, -14, -3.377315706718201, -3.2161432747093484, -3.399124537519932, -3.3301265052167777, -14, -14, -3.397337394738015, -3.525311424457106, -14, -3.547959254186377, -3.2250971960416357, -3.12446873184344, -14, -3.333671396845737, -14, -3.3132060317658674] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1406  total reward: -4555.621756707344
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.048347344686056, -1.047855495959449, -0.9282293762743988, -0.7206370700285238, -0.6634729424335223, -0.6693430803232925, -0.7465543050347075, -0.631611193897856, -0.6400310520402411, -0.6821819800347146, -14, -0.6421735988896615, -0.6646943136931058, -14, -0.6885286781307836, -0.6304096186947302, -0.6237469344647162, -14, -0.6288582679296199, -0.6465349469476568, -0.6265323363432079] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1407  total reward: -4556.886084012234
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1105492178660925, -1.232571388144796, -0.9279902125812912, -0.7998387579744778, -0.6847757531025352, -0.6492401448099443, -0.8343710416391875, -0.6422497825138822, -0.6672864222997729, -14, -14, -0.6602703116843912, -0.6895943092769699, -14, -0.6422497825138823, -0.6450135902207768, -0.646807714756221, -14, -0.6451657019151714, -14, -0.6405803704257126] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1408  total reward: -4558.024350942378
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8203334380167485, -0.8874803138505075, -0.7135362389790436, -0.5594091910607402, -0.5213604713675385, -0.5306907138224912, -0.5743258944432728, -0.5124749288836766, -0.5021765643409, -14, -14, -0.5143166194355222, -0.5414093551618544, -14, -0.5450948158420788, -0.5041178787208136, -0.498348644610374, -14, -0.5023321163765929, -14, -0.49768655971743225] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1409  total reward: -4558.873633665353
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5950842928005997, -0.630850510734202, -0.4999757457642322, -0.3948675265287722, -0.3694453255871062, -0.3734610325498316, -0.41155840515023195, -0.35893811025346234, -0.3557642476454232, -14, -14, -0.3633457278877251, -0.3807165902155434, -14, -0.38281708630518513, -0.35617031152518747, -0.3530880140291977, -14, -0.3542910831266721, -14, -0.35159616325798976] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1410  total reward: -4559.710471419741
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6700969283168043, -0.9722399103866123, -0.6109256789668013, -0.5292106456036317, -0.48348611325265856, -0.49337061307972635, -0.4642816759211851, -0.5021746701076893, -0.4865934419624593, -14, -14, -0.49867954781908663, -0.5182085684777937, -14, -0.5212319918504121, -0.46911491552274054, -0.4515683325040745, -14, -0.4882151738899096, -14, -0.4852415911306319] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1411  total reward: -4560.533716196258
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6343503020918573, -0.6584220637785952, -0.5144067224274318, -0.4315010579631132, -0.39367887657836015, -0.3821562927312011, -0.43842782181842305, -0.3700410690007771, -0.382483313513843, -0.41701993869341875, -14, -0.3814492496048547, -0.3942178784002926, -14, -0.40757317376928776, -0.37418166199388603, -0.37214468516347143, -14, -0.37284506653846655, -0.38461167146894315, -0.3716764440119638] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1412  total reward: -4561.447954916097
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9143278857966886, -0.9448200525869183, -0.7636481879098908, -0.6197280237039008, -0.5741228645026025, -0.5692177543636421, -0.6382484019417713, -0.5392519982033523, -0.5461890676484574, -0.6080065919528441, -14, -0.5552521161239072, -0.5636348986059875, -14, -14, -0.5436016063748051, -0.5672407827224837, -14, -0.5449366710555751, -0.5477846796488256, -0.5441976508381007] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1413  total reward: -4562.8411444620215
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.901231858036659, -1.4221544405324718, -1.0183507449052334, -0.8753233178613603, -0.9036045440281824, -0.8915124289342731, -1.054426908779047, -0.8710294298405463, -0.8625337046588354, -0.8914248603290823, -14, -0.8719929698530222, -0.9021925178918031, -14, -0.9142265801081163, -0.8588524164151342, -0.8499854699286136, -14, -0.8575898490269727, -0.8863465416489884, -0.8539375477209032] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1414  total reward: -4564.590368817606
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4137305395693422, -1.6759071071103777, -1.245242507088191, -1.019995823080421, -0.9327695161758981, -0.9351416203787588, -0.9856237894265164, -0.927273461189836, -0.905361161643795, -14, -14, -0.9319140741119881, -0.9825082652876761, -14, -0.9786183959703356, -0.9056585948651379, -0.8880838011998673, -14, -0.907480950054693, -14, -0.8992388856560617] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1415  total reward: -4566.318365851612
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4026591395141355, -1.455870283942458, -1.1970315697563885, -0.9553918362691373, -0.8852537929904377, -0.885503798628842, -0.9696499787469829, -0.8448777626436229, -0.8606467180014141, -0.9643654215221125, -14, -0.8602677464768881, -0.8863353394380518, -14, -0.9327434248311649, -0.8464216244918533, -0.8469943598718788, -14, -0.8423552493402701, -0.8551679494047744, -0.8399132328061231] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1416  total reward: -4568.050509490888
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5127595645189458, -1.5871550303098894, -1.2379848476258697, -1.0368682900698512, -0.9440917243130463, -0.9177076076188238, -1.0467564058365482, -0.8882628457351089, -0.91862825182133, -1.0184772255535528, -14, -0.912354427920252, -0.939987459271513, -14, -0.9802368994171775, -0.8986838280114468, -0.8922679968122029, -14, -0.8948475049561083, -0.9177725202486724, -0.8922304064698305] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1417  total reward: -4569.894644484702
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5767537456363494, -1.7258030857029418, -1.3244766158164567, -1.127369498677905, -1.0090916592047157, -0.9760859131557269, -1.125014524458358, -0.9609076280064658, -0.9777646798416804, -1.0771542671224845, -14, -0.977906643783447, -0.9941377308874957, -14, -14, -0.9552840374600796, -0.9829612846790415, -14, -0.9576902478152614, -0.9685071367137833, -0.9558721480793664] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1418  total reward: -4571.854968563714
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7459385447685, -1.7173109313645587, -1.3993680462616958, -1.1565791074033906, -1.0679501400990281, -1.0415898418544782, -1.2132607865196106, -1.0010426775756527, -1.0043494661222871, -1.0622508417055432, -1.037403734956659, -1.0282698081129387, -1.043890522375218, -14, -14, -1.0041884492181694, -1.0256737037510162, -1.0192897957885634, -1.007405172330882, -1.0159929460420642, -1.0050400415520044] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1419  total reward: -4573.775678917054
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5573766386223407, -1.5700288715989694, -1.3214604980563396, -1.0556081313319787, -0.9736024023857172, -0.967661417260498, -1.0651215134273946, -0.9211965810970776, -0.9380529339747099, -1.0023421269855348, -0.961346495611692, -0.9419332565540381, -0.9646729528635435, -14, -1.0053634837784955, -0.9128683039792606, -0.9280131388684096, -0.9386824502453643, -0.922595527323448, -0.9390207494428586, -0.9196676757648566] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1420  total reward: -4575.612627964194
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6052065316235407, -1.6259235854736513, -1.3294950599163504, -1.054124667222137, -0.9787865188674675, -0.9765225442224207, -1.0870318201145885, -0.9238114853342508, -0.9447102502880721, -1.0429270401142117, -14, -0.9465377259301839, -0.9752741713651155, -14, -1.000316803343594, -0.9307451033038612, -0.9276905159020862, -14, -0.9266424111499902, -0.9443631421436068, -0.9240807431606461] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1421  total reward: -4577.33566759673
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3841207693293303, -1.3172092946190372, -1.1563373136398367, -0.9005996842981707, -0.8471309943851827, -0.8569999987045994, -0.972772629983582, -0.7789958240102864, -0.7973716860109474, -0.830397663120106, -14, -0.8132079513029986, -0.8277004770202341, -14, -14, -0.800789328869677, -0.8143188241573077, -14, -0.8005096344535928, -0.806983559542183, -0.7992281472013114] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1422  total reward: -4578.862247776957
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2922658976612058, -1.2674944939375283, -1.0889965591057627, -0.8584203158984186, -0.7939730049036828, -0.7923950344135514, -0.9008698348132377, -0.7652052274635515, -0.7557512927289585, -0.8005360296447521, -14, -0.7634137246860484, -0.7881409289091384, -14, -0.8091356717002862, -0.7535982788986588, -0.7476848921734499, -14, -0.7502864041629516, -0.7712191346338163, -0.7475843562160106] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1423  total reward: -4580.365481917436
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2868799044122852, -1.303987567291576, -1.0445398960520045, -0.8713601304104265, -0.8004641653026503, -0.7797468958015897, -0.8965712176438649, -0.7648953409074224, -0.7725361933556574, -0.832277720647156, -14, -0.7734537312890086, -0.7974866616856818, -14, -0.8403142688094604, -0.7602463536341735, -0.7540544310188924, -14, -0.7576829022541965, -0.7823688043447573, -0.7556497842638328] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1424  total reward: -4581.922081231838
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3083747089479216, -1.495551644966948, -1.1070325884967867, -0.9402472232953489, -0.8420138482036935, -0.8202532314199894, -0.939246149460218, -0.8139861705060976, -0.8154156686431168, -14, -14, -0.834046950518652, -0.8756022305554692, -14, -0.8739502329612523, -0.8129907801971649, -0.8054038017304789, -14, -0.8082004061975038, -14, -0.8025448833827634] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1425  total reward: -4583.729490258862
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.1591518181786271, -1.005439431896086, -1.0522199435100577, -1.0555284062149535, -1.1969550959696837, -1.0669608985954444, -1.0066039017867383, -14, -14, -1.039199210207811, -1.0917970062198477, -14, -1.1153347648502845, -1.0191880905574748, -1.0108089115916854, -14, -1.0133378683361653, -14, -1.0048641436404564] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1426  total reward: -4585.527535573207
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3785170301525718, -1.4497180134479672, -1.0833264383077383, -0.9004919985502321, -0.8367941544883578, -0.8204488628481902, -0.9488653100130727, -0.7986189864011658, -0.8100286400633082, -14, -14, -0.8211964448325563, -0.8607014329464611, -14, -0.8623829041956275, -0.8035409969859009, -0.7989319148997855, -14, -0.7989971719480008, -14, -0.7931811707053964] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1427  total reward: -4587.058779511062
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2300084059208845, -1.3261333587858806, -1.031745712521057, -0.8094796921252805, -0.7703498311711017, -0.7907719302324903, -0.8258991099812851, -0.768751307463593, -0.7398683761778996, -14, -14, -0.7634406165705944, -0.8037521522568976, -14, -0.7993098092935444, -0.7449827665868988, -0.7306146540687337, -14, -0.7448030286681805, -14, -0.7380627671499815] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1428  total reward: -4588.54608637057
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3420116593618157, -1.3293641712112192, -1.041983122355342, -0.8652695060006352, -0.8037335251071098, -0.7827281376365681, -0.9042821402629655, -0.7622526102171805, -0.7717617398675322, -0.8456778677925892, -14, -0.7730758994229298, -0.797057851289259, -14, -0.8252613243855024, -0.7620599619283532, -0.7567662261522127, -14, -0.7591113179292746, -0.7771896599994531, -0.7566922054392883] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1429  total reward: -4589.668861738005
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3768476893409002, -0.3728182170761677, -0.46227656403550643, -0.4415151603185033, -0.3621991812295555, -0.3648542616720491, -0.3681469028084672, -0.45425224824851285, -0.36678102012503044, -0.37304444126860087, -14, -0.3842949544735062, -0.4069130268933026, -14, -0.49991837577930553, -0.3676469911521718, -0.37033599826455876, -14, -0.3690259096622373, -0.39020029766564196, -0.36608316199519453] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1430  total reward: -4590.682671303939
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9887334666934433, -0.945904040700281, -0.9124169931608892, -0.7553735110564592, -0.6134562113619106, -0.669605270610234, -0.7449808772978659, -0.6588705104309502, -0.6613152918766694, -0.7270050076027083, -14, -0.6657024086312419, -0.6880273931199951, -14, -0.6972582457562427, -0.6562448174229413, -0.6429392313473655, -14, -0.653654509687318, -0.674468315716679, -0.6516103847048025] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1431  total reward: -4591.757214031431
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8362125776824662, -0.7899693816343787, -0.6533124636630457, -0.514426096155919, -0.4894703093031006, -0.4917987557819944, -0.5518107765625422, -0.46464365727315887, -0.4689681723494667, -0.5037129091618545, -14, -0.4719919302711011, -0.48561024107159945, -14, -0.4977157692010793, -0.46454047932476683, -0.46058628858507966, -14, -0.4620703881175083, -0.4747783656073409, -0.4610865161305558] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1432  total reward: -4592.608544315189
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6371288735707465, -0.7036304044054426, -0.5344374356624526, -0.43382322168127824, -0.407326073830581, -0.4100561516180286, -0.4370789380164854, -0.40984378119048714, -0.39165948726739647, -14, -14, -0.406786964843864, -0.43071044400718295, -14, -0.4274833437241741, -0.39439359950257946, -0.3868225583954745, -14, -0.39449004143148325, -14, -0.3907439951720589] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1433  total reward: -4593.376587975974
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6533424675111661, -0.6623996166461591, -0.5523944467937922, -0.43861927125532946, -0.4040185904790999, -0.4021294490732651, -0.45156978822796323, -0.3875595195651844, -0.38674451488900197, -0.4224694109995262, -14, -0.389417608918353, -0.3979132524564579, -14, -0.41466405476026374, -0.38429471532201315, -0.38034250943153125, -14, -0.3814576933555251, -0.38838678013147115, -0.3812211023900868] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1434  total reward: -4594.103393044193
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5830116951939657, -0.6057010593114818, -0.5031389494649403, -0.39274537837416923, -0.3650909264767802, -0.3699951501677721, -0.4169051157777879, -0.3596806672317101, -0.3483784583385691, -14, -14, -0.3570080930981792, -0.3717095636328707, -14, -0.37923886807171864, -0.3516646915086174, -0.34924658895787286, -14, -0.34859885692307746, -14, -0.3464625587867719] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1435  total reward: -4594.807801462146
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6005796010934806, -0.6479562660814497, -0.48835965605425696, -0.39953355835410503, -0.374864450117035, -0.3738514863476261, -0.4100936393350338, -0.37231382875073077, -0.35960528088682675, -14, -14, -0.3706710707224385, -0.39103929869077036, -14, -0.3913694865293447, -0.3624009510376427, -0.3568312087521372, -14, -0.3613777017543787, -14, -0.35794585916714816] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1436  total reward: -4595.714495860131
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.192483820021076, -0.9081240087222828, -0.6315400099329584, -0.5588579419334374, -0.5791818337087294, -0.5668112503728612, -0.6596447136419404, -0.5757852324114474, -0.5538631183870312, -0.5811890028158267, -14, -0.5604335617569791, -0.5751465763644393, -14, -0.6064976235591766, -0.5541957680851525, -0.5491917791915488, -14, -0.5510591486114639, -0.5621703222255429, -0.5498631892332083] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1437  total reward: -4596.8701830979535
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9878300106047133, -1.1192926014892022, -0.8443264781455698, -0.6919739990608642, -0.6339375721551068, -0.6304085991119475, -0.6906971635397358, -0.6204982997436692, -0.6132060865948589, -14, -14, -0.6280938157685891, -0.660302049474387, -14, -0.661310777245343, -0.6135488452174136, -0.6055315091870805, -14, -0.6115388514095433, -14, -0.6064954586292671] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1438  total reward: -4598.24021411297
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2769113683114683, -1.3825379705360017, -1.056577278460646, -0.8874646033156998, -0.8060280984362217, -0.7851723796425302, -0.8802548009189619, -0.7620814330349697, -0.7862931097759445, -0.9104246597876923, -14, -0.7812659956561814, -0.8015305032419777, -14, -0.8406927758747859, -0.7703819991006844, -0.7766587969400932, -14, -0.7660534197382686, -0.7816162053252524, -0.7644995058306209] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1439  total reward: -4600.070767423464
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8115653789571273, -2.0857791107484025, -1.4797362061777113, -1.3131605188155122, -1.13332290678622, -1.0753674769933086, -1.2799239879353057, -1.0721148346610319, -1.3647803914815573, -1.2462114350645492, -14, -1.1029498038106804, -1.1374218432569199, -14, -14, -1.068220537686377, -1.0674191388899028, -14, -1.0781142842470453, -1.14303337441471, -1.068471877457878] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1440  total reward: -4602.027694131324
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4112517820715587, -1.619057472996214, -1.2316771095035244, -0.9955811090004462, -0.9240144720018284, -0.9335439879396431, -0.9799036049453672, -0.8575760436402343, -14, -14, -14, -0.9209198923783679, -0.9696593567891629, -14, -14, -0.8784052733521873, -0.8563590199152108, -14, -0.8974644411158755, -14, -0.8895075689710356] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1441  total reward: -4604.234068057134
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8262474717514527, -1.5294630365780346, -1.3981729266498397, -1.3886303599762468, -1.4416895214915866, -1.3509084983978152, -1.3792003575952598, -1.9255318478189165, -14, -1.3599416723680744, -1.360823331174132, -14, -14, -1.3331131519934591, -1.4765139363777255, -14, -1.349791726774105, -1.3554427666263211, -1.3500149058941537] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1442  total reward: -4606.480051647195
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.575218116590641, -1.5178311415277792, -1.273793586143389, -1.022715919364036, -0.965642785623023, -0.9639356183383962, -1.0832110604668914, -0.9077984096216695, -0.9143247915976623, -0.9615899260481234, -0.9425265552205696, -0.9351336037336082, -0.9542425913006161, -14, -14, -0.9121812861546775, -0.9342694613070769, -0.9248630544390832, -0.916903164328302, -0.9201941733494161, -0.9128704380678837] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1443  total reward: -4608.276116264654
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.498932225423951, -1.5707640355742605, -1.221433383154755, -1.0284038449585458, -0.9389089064377667, -0.9118959121030443, -1.0174227001644707, -0.8823070588576495, -0.9116633759374647, -0.9878351094199146, -0.9295410714653776, -0.910285786589108, -0.9324517266998983, -14, -0.978567304115596, -0.8814459908478717, -0.8976478208469666, -0.9067834336947984, -0.8912784139594407, -0.904985672055398, -0.8882662078371073] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1444  total reward: -4610.341369444655
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.077044284909474, -1.946616035687833, -1.8369556288741264, -1.3292181251789303, -1.2564647256443346, -1.328103754443881, -1.4300914188938922, -1.1998116907260654, -1.1981899419983566, -1.2640483464213712, -14, -1.2051171210056086, -1.2393196230967605, -14, -1.264811192208148, -1.1902797365067426, -1.1757811713905537, -14, -1.1873351713916964, -1.2211205110977006, -1.1838071891541206] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1445  total reward: -4612.225509504785
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2246886615383537, -1.3014797198802628, -0.9706397459937379, -0.7979795205583948, -0.7454513668763111, -0.73680294061784, -0.8317089392003665, -0.726856657499519, -0.7147328809649429, -14, -14, -0.7311547245294373, -0.7615305305346524, -14, -0.7708284117372941, -0.717967723812113, -0.7113234973831231, -14, -0.7125439888678062, -14, -0.7083588887384962] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1446  total reward: -4613.549461445636
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9820483004981642, -1.1457683712689681, -0.870291282047042, -0.7039831345011036, -0.6411575777548173, -0.6431757963806292, -0.6888694705898077, -0.6290460827094324, -0.6214311449300509, -14, -14, -0.639034795452132, -0.6749262165319334, -14, -0.6658744315334224, -0.621584675387678, -0.6114470971964939, -14, -0.621372130822451, -14, -0.6155930521123569] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1447  total reward: -4615.077137403277
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3849555060377536, -1.750271265098168, -1.2434714285160664, -1.045650660040099, -0.9423047446261356, -0.9400532371804621, -0.9607109600142716, -0.9195308719806442, -0.9415656655912951, -1.3683490374751361, -14, -0.9241787825393348, -0.9284937308179836, -14, -1.0320382165342659, -0.9179357065069798, -0.9716307930135977, -14, -0.9158840405089435, -0.9144626490803652, -0.9162288604452167] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1448  total reward: -4616.832076640441
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.482634376607043, -1.428903348646952, -1.1838221231234258, -0.9670548623486086, -0.8946486520429624, -0.8764284830129132, -1.0982550976974597, -0.8403979111598886, -0.875294270353854, -14, -14, -0.8521760982060622, -0.8610414279957268, -14, -0.9491911582440579, -0.8436712037982931, -14, -14, -0.840873361565637, -0.821809099614577, -0.8404765880839613] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1449  total reward: -4618.529424790011
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.565737492077058, -1.5291372136460208, -1.2204005956746669, -0.9830685946246341, -0.9281396600550015, -0.9209876185732288, -1.0348592676498642, -0.876186680434892, -0.8958831456086698, -0.9884399479423103, -14, -0.8954319707961452, -0.9219679377221957, -14, -0.9529283023036811, -0.8818006138436041, -0.8777979956693477, -14, -0.8779053794972758, -0.8991164985838843, -0.8755390499550658] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1450  total reward: -4619.808409304635
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4114715570534856, -0.4078802649353078, -0.5130060494461129, -0.4685660107962173, -0.4008738701439345, -0.40445536619996136, -0.40542422966261427, -0.5087944965455111, -0.4038679485708008, -0.4125678679996594, -14, -0.4220300295413454, -0.44341842601645504, -14, -0.5570752043320794, -0.4045070505261855, -0.4070995983279873, -14, -0.4057701945559622, -0.4318172575662101, -0.4034454646686143] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1451  total reward: -4620.978819618015
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.206196736569808, -1.1728842832380044, -1.0523406308347067, -0.9250299033646249, -0.7191205878388368, -0.7732386426240622, -0.9007419743992422, -0.7609631320215147, -0.8061478852564726, -0.8981478667513406, -14, -0.7905230482216444, -0.8227670001077164, -14, -0.7609631320215152, -0.7688886672769735, -0.759303621460087, -14, -0.772891354586203, -0.8193788331714421, -0.7695364432362204] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1452  total reward: -4622.32343906146
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.065615176809146, -1.1128442034354804, -0.856347255631397, -0.7271964046930839, -0.6622732463166141, -0.6401191572313712, -0.7364783113092397, -0.6262496078879073, -0.6416402842655559, -0.7134723606709882, -14, -0.6414410574599476, -0.6622938143076131, -14, -0.6884545356246634, -0.6303389676825566, -0.6274120540589564, -14, -0.6274488647604465, -0.6395183028814149, -0.6254988556055776] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1453  total reward: -4623.625145265412
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1135044476987457, -1.219604563884664, -0.9235112278784916, -0.7939458429520372, -0.7128950281322758, -0.6883943681816298, -0.7816532016051466, -0.671739368245639, -0.6994540687372117, -0.8045134277581819, -14, -0.6943223475822943, -0.7167310799114451, -14, -0.7517694196071247, -0.6808671840286247, -0.684169777768767, -14, -0.678271796958493, -0.6908110318499686, -0.6762073483465058] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1454  total reward: -4624.655086521473
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6214229672692654, -0.6238953672112932, -0.49780653772545685, -0.41127963001092177, -0.3799573476447528, -0.3712827032987614, -0.43194134264067924, -0.3541822570059502, -0.3580498381058114, -0.39369305377338554, -14, -0.36473356057176887, -0.3712580411533451, -14, -14, -0.358316003449128, -0.3683772347096705, -14, -0.3589521452447347, -0.360517713155515, -0.3582018878158107] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1455  total reward: -4625.3126919506485
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5205446271404234, -0.5261747210435924, -0.4173786349556286, -0.3488197962878532, -0.3214474971044825, -0.31294475381506787, -0.3596635996766681, -0.30619643110741873, -0.31026205319320876, -0.3362905375976852, -14, -0.31118592595286215, -0.32112726597167696, -14, -0.33568204736344154, -0.305644751422371, -0.3037066175014551, -14, -0.30423594134529214, -0.3132914427105985, -0.3034231721698161] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1456  total reward: -4625.947352933282
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7265353712146202, -0.5298828242632714, -0.40043168964307346, -0.33484389694135763, -0.34830450375004784, -0.35534009822043683, -0.40331895148410785, -0.3441117005858728, -0.33376952648691804, -0.34271714539098413, -14, -0.33805542450687603, -0.34763121650925016, -14, -0.3609671482760601, -0.33305122996763065, -0.3287481552366221, -14, -0.33201755981461456, -0.3410746370655389, -0.33123781046300843] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1457  total reward: -4626.5033561919045
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.369154788063122, -0.3991210267844674, -0.325954946658481, -0.2495267349538882, -0.23684796242645006, -0.24720069389792454, -0.25406555024352523, -0.23765410961174468, -0.2279830097768602, -14, -14, -0.23547199135868882, -0.24855486753978706, -14, -0.24873967879256426, -0.2295403228601074, -0.2257107219393102, -14, -0.22944779987398178, -14, -0.22725510338642838] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1458  total reward: -4626.981104863433
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4492485982039444, -0.46950194680343454, -0.34368177773894615, -0.31192900826987996, -0.2707502784021766, -0.2528111134302447, -0.3167863745303588, -0.25077863733711314, -0.26876587303672844, -0.28138407833086276, -14, -0.2586622652329511, -0.269388822500162, -14, -0.25077863733711325, -0.25096042860754547, -0.24985869866137533, -14, -0.25339042207572815, -0.2715522341201877, -0.25203794958864023] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1459  total reward: -4627.503640941616
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4522053265827197, -0.5188114379406862, -0.36478134042660587, -0.30206793775519847, -0.2834826180541176, -0.28288124526480674, -0.2967307474589872, -0.2794158690582882, -0.2742317431533832, -14, -14, -0.2832987857186282, -0.2990382783869966, -14, -0.29213318848324643, -0.2741852535944287, -0.26776444964312074, -14, -0.2751253404920813, -14, -0.2726773795219252] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1460  total reward: -4628.119534335283
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6026388350142627, -0.6213529749182217, -0.4838384718520908, -0.3970271958125399, -0.36811573843574646, -0.3618438541444988, -0.4053260741642678, -0.3483808092499843, -0.35659913747485966, -0.4079925858248486, -14, -0.3557749403112702, -0.36570673593931763, -14, -0.38095512377201857, -0.35086937658978645, -0.35130162913928625, -14, -0.3490293065951171, -0.35375195960796146, -0.3481289440233663] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1461  total reward: -4629.07444549721
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0428820311448868, -0.9520686117233299, -0.9741046608541222, -0.6710209344172845, -0.6418212889007645, -0.7101074199339348, -0.7304908609076886, -0.6270134875346561, -0.6103546110241074, -0.6312000392326239, -14, -0.6184242647481142, -0.6379502551805896, -14, -0.6500498860940535, -0.6102837761481174, -0.603900934049452, -14, -0.6091189671779416, -0.6222194305510949, -0.6067822179044308] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1462  total reward: -4630.326475041427
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1747811629933458, -1.2495692932381628, -0.8791929788161212, -0.797701074002275, -0.6954058158771121, -0.6501069102358118, -0.8597577736053508, -0.6502345443336266, -0.6818178277595253, -14, -14, -0.6680246662704761, -0.6978864325291539, -14, -0.6502345443336266, -0.6521466844666411, -0.6547855990917073, -14, -0.6528369079884093, -14, -0.6481286101672932] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1463  total reward: -4631.658346804724
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4500849076615483, -1.1336721947634876, -0.806065959716265, -0.679715828848941, -0.7146172804136803, -0.7354283299765346, -0.7992050654945242, -0.7326436828233955, -0.6832033544529441, -14, -14, -0.7044762270412247, -0.7360049903980875, -14, -0.7504720618467964, -0.6931318461045313, -0.6855848404836584, -14, -0.6887837017343578, -14, -0.6837431531295688] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1464  total reward: -4633.072257260238
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0852927625238957, -1.8825002774795465, -1.6581655766951695, -0.6558618945289213, -0.7679938555385107, -0.7406376937108365, -1.0578684388183863, -0.7518967294932829, -0.7403529573228108, -14, -14, -0.7586314382671215, -0.7983702869991564, -14, -0.794218444654568, -0.7511701963563302, -0.7460461803039103, -14, -0.7409964250729176, -14, -0.7341946266652556] argmax 3
Action chosen: switching off line 3
  Simulating cascading failure
  ok
timestep 1465  total reward: -4634.315574486825
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9338204012146596, -1.126881711817395, -0.764571836121838, -0.6669883963302541, -0.6084516864145871, -0.5958080776552825, -0.637212898951683, -0.6077718179455139, -0.589933902927385, -14, -14, -0.6108970760823345, -0.6489733067613324, -14, -0.6354214114278072, -0.5902974278015672, -0.5746861126743631, -14, -0.5939650574541571, -14, -0.587455332058578] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1466  total reward: -4635.454582701989
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9630094042322075, -0.9881692372407912, -0.7877574357521184, -0.646913084737831, -0.5968516350651869, -0.586299033871847, -0.6613841286419879, -0.5702174640340332, -0.5757783503449825, -0.6361479098593898, -14, -0.5776240000101738, -0.5941129072952349, -14, -0.6214748525071174, -0.5687434499623, -0.5691861527656994, -14, -0.5655839201417662, -0.5796944590970433, -0.5643221024887255] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1467  total reward: -4636.642949012388
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0864533871743514, -1.0868681465398788, -0.8829550007541667, -0.7159742776837477, -0.662148124965462, -0.6520633498096292, -0.7432664888346143, -0.6240032831343689, -0.6391984236595443, -0.7028349313059397, -14, -0.6377853318066083, -0.6552353125704649, -14, -0.6798617941775106, -0.62867866099177, -0.6209556795309833, -14, -0.6252762679842524, -0.6399975711874449, -0.6240442079105314] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1468  total reward: -4637.776203182183
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.845720956161801, -0.917859492937584, -0.7110020963122131, -0.5751008207496978, -0.536321179825689, -0.5376669793583086, -0.5887878516757376, -0.5314236239182305, -0.5167168639824803, -14, -14, -0.5291954302197992, -0.5571003775686164, -14, -0.5675484538267328, -0.5189741498615272, -0.5132079129064508, -14, -0.5171474666840755, -14, -0.512298490264061] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1469  total reward: -4638.791324918978
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8506311088030543, -0.9201847589384891, -0.689210084448583, -0.5628540205338312, -0.5270716086812325, -0.5251404295241817, -0.5774312072239709, -0.5217352105121856, -0.50473293104827, -14, -14, -0.5201591717983306, -0.544107596975742, -14, -0.5453161655871369, -0.508953534405428, -0.5012048620868579, -14, -0.506266755299077, -14, -0.5028232465303052] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1470  total reward: -4639.777959869457
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8755883486640746, -0.8439833161647741, -0.684840903009605, -0.5489897535639231, -0.5159913993228977, -0.511279435060375, -0.5827501117468129, -0.4882229361577122, -0.4944075041953128, -0.53899120028004, -14, -0.4947764174074931, -0.5078120485855442, -14, -0.5242934675431042, -0.48888313425314245, -0.48318901852046875, -14, -0.48647641915912243, -0.4985741190602169, -0.48543008839242] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1471  total reward: -4640.706373002229
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7222502735488463, -0.8042131134507824, -0.617933465458062, -0.5015100471542436, -0.4648922616964901, -0.46606998259258325, -0.5046921576538783, -0.45791277471478553, -0.44944366092964466, -14, -14, -0.4626911864113816, -0.48992498508263843, -14, -0.4874424920988312, -0.450217265683418, -0.44329150663683164, -14, -0.44969234997216306, -14, -0.44522411425223535] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1472  total reward: -4641.802063449621
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1485711258847044, -1.103683494791415, -0.965268547729037, -0.7434237754413984, -0.6935859282754543, -0.701205691215271, -0.7895119281252808, -0.6537360984709013, -0.6655324350164457, -0.701299781033808, -14, -0.6656616668071402, -0.6850506911946278, -14, -0.7022558769434427, -0.6558033662074746, -0.6461857354898062, -14, -0.6540769060417458, -0.6791416820855694, -0.6523989407548416] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1473  total reward: -4643.056779555147
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9676187897320223, -1.133523806722136, -0.847521977622745, -0.7120136382014566, -0.635783469119121, -0.6243906240972704, -0.6981028850241715, -0.6208600706771858, -0.6155272200768446, -14, -14, -0.6319272205771176, -0.6692196870326735, -14, -0.6609506025047398, -0.6160582350888847, -0.6067429698683656, -14, -0.6147873747221595, -14, -0.6085303700363162] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1474  total reward: -4644.145103664317
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8427523442607306, -0.8550969108308142, -0.6437130694300958, -0.5453281971983323, -0.5092705203664711, -0.4945710857721692, -0.5614852004626947, -0.48434420811171697, -0.49328218281597475, -0.5546246911118922, -14, -0.49168123230519656, -0.5051815517386176, -14, -0.5330390451496454, -0.48532901009074497, -0.4860510832208576, -14, -0.4827576869812297, -0.4945848068665598, -0.48158113930099733] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1475  total reward: -4645.059133556884
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7676565300670651, -0.7465749202246411, -0.6131956692949092, -0.48840662914785193, -0.45884016947809847, -0.45715056050207714, -0.5152406669265686, -0.43235894978922085, -0.44290555735116915, -0.4738899306469642, -14, -0.4427735339850755, -0.4567999273387075, -14, -0.4707684312755348, -0.43483434122139214, -0.43043745332912664, -14, -0.43370827846370597, -0.4472823984097506, -0.4324487532674769] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1476  total reward: -4645.951959383805
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7832750596523624, -0.8627470119141567, -0.6225637201187019, -0.5161758860241401, -0.48373754986224615, -0.4793955171716887, -0.5224149303292203, -0.4721368594295548, -0.46719322587603346, -14, -14, -0.4781590569308407, -0.5048832730171662, -14, -0.5010640909718591, -0.4673680090930248, -0.4602074698062897, -14, -0.46714847860674236, -14, -0.46238837359070767] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1477  total reward: -4646.871387718232
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7648327501690807, -0.810070660330813, -0.6610697711371466, -0.5309479434950434, -0.48469286082423796, -0.4811309109778847, -0.532761083626203, -0.4604063800116982, -0.4705234429065962, -0.5230030782430131, -14, -0.4689179473714885, -0.4816519715166358, -14, -0.5051381209166865, -0.46248673393013057, -0.4609092590767625, -14, -0.4603155829612441, -0.4701567007837235, -0.45922086462075373] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1478  total reward: -4647.6003238802
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.46769621372277514, -0.46209249404204095, -0.3752928413756261, -0.3046514673942012, -0.2854195004908877, -0.2825425922171314, -0.3180765018848681, -0.272121805511794, -0.27581461994615036, -0.2977189993500805, -14, -0.27652635876740334, -0.2849376905464212, -14, -0.298467546190265, -0.2717067558234115, -0.2694128016189794, -14, -0.27034883006876037, -0.2776175200121983, -0.26971529734838745] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1479  total reward: -4648.117230205173
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.39971710977803554, -0.4518697286770502, -0.3310240973408968, -0.2759762858751617, -0.2574840518174776, -0.2561993492110075, -0.2740342819471744, -0.2520838628330019, -0.2521400886839006, -14, -14, -0.2575516752612719, -0.27330886971424434, -14, -0.27435360553101035, -0.2500426468674981, -0.24593802544781962, -14, -0.2500914529022463, -14, -0.24749352335351393] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1480  total reward: -4648.648295106289
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.49104852325324744, -0.45813722072968105, -0.45153076272835535, -0.3186258877440219, -0.30202560185386307, -0.326212910393847, -0.34302809111024846, -0.29161525670657434, -0.2878028862856394, -0.3006704458946873, -14, -0.2905469984874783, -0.29836986735337817, -14, -0.30575578888857796, -0.2867288744937821, -0.283323751017942, -14, -0.2857787456342267, -0.294040307656813, -0.2851268756680404] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1481  total reward: -4649.1167291438105
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.30890663867359247, -0.33110314259550033, -0.2620982154648848, -0.20437857270412949, -0.19356164118059874, -0.19874448385725774, -0.2098975623606176, -0.1923202547472452, -0.1859123532211775, -14, -14, -0.1913193850104063, -0.20190725958131606, -14, -0.20171708279406772, -0.18728433364780903, -0.18438138339035087, -14, -0.18700743813958776, -14, -0.18511028650343261] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1482  total reward: -4649.4611373584485
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.2704906192481665, -0.28243711873464616, -0.22191556144322935, -0.1861209803440428, -0.16936955633207787, -0.1645316180779817, -0.1883279082546838, -0.159723953452773, -0.16459133503679108, -0.18118368182849012, -14, -0.16373714258386826, -0.16891324595812002, -14, -0.17633462787977475, -0.16115560675172919, -0.16026985806283672, -14, -0.16052863582269952, -0.1655064890737367, -0.16002683124815134] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1483  total reward: -4649.840614570625
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.38016449178164063, -0.3927197789951413, -0.30134962284475275, -0.2513999371853224, -0.23247470762509656, -0.2267883667247312, -0.25956698770063746, -0.21931300075142796, -0.22172049325966997, -0.24826219750814577, -14, -0.2235981626646405, -0.22713404180697494, -14, -14, -0.21942404222974143, -0.2270890448536517, -14, -0.22020048144342663, -0.22168064365374257, -0.21975325872356877] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1484  total reward: -4650.322789392142
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.43635935844212576, -0.45449723663173847, -0.3773122829670803, -0.29967042184644327, -0.27699709657076893, -0.2777121780183872, -0.3034178673556255, -0.2652043631231379, -0.2688841450631146, -0.3025559181078541, -14, -0.2690792989122925, -0.2761840537080738, -14, -0.2918669880005341, -0.2649081983035497, -0.26560193718901937, -14, -0.2633295627369469, -0.2682060457887626, -0.2628618207656997] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1485  total reward: -4650.980319283865
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7054421712999754, -0.6961090658022246, -0.5510423356467195, -0.4501642738986963, -0.41939260192641986, -0.4112239773826891, -0.47172499833429143, -0.39477722771603463, -0.4032881363486464, -0.4442696066366049, -14, -0.4024459744272069, -0.41476655825363856, -14, -0.4265439204534355, -0.39758503280819174, -0.39362600383898766, -14, -0.39607272544667016, -0.40418887521260366, -0.3946680709576505] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1486  total reward: -4652.056880496384
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.194010075576676, -1.1279471528347325, -1.0832085738460384, -0.754513678840091, -0.722124578877447, -0.7921873743733098, -0.8519745974426779, -0.7078161483186817, -0.6843397283897279, -14, -14, -0.6979412773036608, -0.720508863838117, -14, -0.7322065624065325, -0.6925122715251528, -0.6905642252555808, -14, -0.6865010200760813, -14, -0.6829352086795397] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1487  total reward: -4653.165166098139
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6940870212880366, -0.7734956565549118, -0.5826280168766327, -0.48209085648660815, -0.4447128087033703, -0.4409026714782371, -0.4858257126684146, -0.440039076374923, -0.4280889356965443, -14, -14, -0.44152849538809574, -0.4670303873408857, -14, -0.4647567591887534, -0.4304882088807616, -0.42322686386930136, -14, -0.4295814890764668, -14, -0.4253503930751831] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1488  total reward: -4654.075476814789
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8178702087297612, -0.8342194759947227, -0.6879533610573862, -0.5643619873535882, -0.5157855621797843, -0.5058738009510417, -0.5780968731093413, -0.49356608934992063, -0.4972289741319121, -0.53724080767275, -14, -0.4976698482850167, -0.5132322832826018, -14, -0.5395969562004548, -0.4906418940977434, -0.48631403197303663, -14, -0.48861169423722933, -0.5037814956904824, -0.4870838527807994] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1489  total reward: -4655.048922949044
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8209236278282772, -0.8963340566128369, -0.6644350347726763, -0.5497529633043216, -0.5108511081387447, -0.5050649917782858, -0.5618266573837142, -0.5021542506399104, -0.490651608376853, -14, -14, -0.5046240335354152, -0.5304582448741113, -14, -0.5307497855924947, -0.4933791190007947, -0.4867264314075729, -14, -0.49113561847573195, -14, -0.48713210228121384] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1490  total reward: -4655.9909788807245
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8027493514027053, -0.8086642413173398, -0.6324114464962988, -0.5195753687456887, -0.48282898098762356, -0.47308698726270226, -0.5376908093101617, -0.45426838912215733, -0.46691695734848393, -0.5149422644166315, -14, -0.4666310400016005, -0.47877981640642164, -14, -0.49562503847678774, -0.458492998378138, -0.4543594230235354, -14, -0.45591150141848413, -0.46607990669084937, -0.45532950027323016] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1491  total reward: -4656.9511250222495
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9112751495484112, -0.8810531258245735, -0.7139729702261045, -0.5825780718161251, -0.5395520404350145, -0.5270100209157493, -0.6282094190444145, -0.5057025437579388, -0.5078564621617689, -0.5350584733115017, -14, -0.5152171899785892, -0.5257913901938657, -14, -14, -0.5064051095205445, -0.5106121931812743, -14, -0.5072687974718698, -0.5205951849186238, -0.5058777524024005] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1492  total reward: -4657.829406278632
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6168145491110311, -0.6723482824491396, -0.5052427692273227, -0.4363807552081258, -0.3928991551739741, -0.3788072601792196, -0.43082141862971074, -0.3744558820172738, -0.38212812441102734, -0.43603490856552507, -14, -0.38097876155489807, -0.39102583575730376, -14, -0.41417390108830104, -0.37559344415938795, -0.3757246048581934, -14, -0.37330773472679507, -0.3793094745843081, -0.3725787126251842] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1493  total reward: -4658.564344821112
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6271181330971033, -0.627196454138341, -0.504908469097764, -0.41432321326576627, -0.38402488845903354, -0.3768825703602036, -0.42984789978953464, -0.36490720189222553, -0.3703411408168733, -0.39669050693532515, -14, -0.3713944037763379, -0.3825627678490961, -14, -0.3980739192180923, -0.3649597836365937, -0.36189170620768507, -14, -0.36315663908832546, -0.3758155911269975, -0.3623598298549774] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1494  total reward: -4659.285519854631
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6055724031015974, -0.6580021719344769, -0.49633906310660925, -0.40219171020506916, -0.37641821711961104, -0.3766027600519238, -0.4113076300973015, -0.36863889384474674, -0.3624651675372035, -14, -14, -0.3711697888656118, -0.38877425893013917, -14, -0.3907050511122132, -0.3634812584573483, -0.35903377563842004, -14, -0.36201972783733327, -14, -0.35928332731119506] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1495  total reward: -4660.015809480827
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6184331753025152, -0.6402374292306193, -0.518526953915824, -0.43026876094942973, -0.39252330017940024, -0.38366860653794205, -0.43707730846891335, -0.3768177300488458, -0.37901185831294715, -0.4164540803620331, -14, -0.38051353761980683, -0.3927165534728827, -14, -0.41350681240088466, -0.3741055069345036, -0.3733269230922398, -14, -0.37234700625852646, -0.38130984334087575, -0.3712558505568199] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1496  total reward: -4660.931320103453
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9657094280322914, -1.0154933429280408, -0.7681654161221885, -0.6730011386694486, -0.5842983091895648, -0.5495866046831831, -0.6807489269911334, -0.5410535267126565, -0.5749402590453476, -0.6022350649596595, -14, -0.5578592346750914, -0.5791381209356904, -14, -0.5410535267126565, -0.5424182210473092, -0.5389960530961218, -14, -0.5467629550196322, -0.5854322608768641, -0.5442547720696462] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1497  total reward: -4661.993052609095
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9073323754660562, -0.9250971363538851, -0.7429317096957514, -0.571182594809207, -0.5487772653450116, -0.5678966104824549, -0.6054588309449671, -0.5411652590163257, -0.5252044566384263, -14, -14, -0.5391380469905337, -0.5645030223606569, -14, -0.5673948051879413, -0.5294431689466922, -0.5233784474275452, -14, -0.5268632959793137, -14, -0.5227364525455522] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1498  total reward: -4662.961961302708
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7875103331765966, -0.8638927520058932, -0.594246463132356, -0.554797528150972, -0.47733235381625916, -0.4459895600841656, -0.5840768101118304, -0.44817632584771644, -0.4782321455511226, -14, -14, -0.4599794464915268, -0.4810974077831243, -14, -0.44817632584771644, -0.4480689245104928, -0.4504080964673913, -14, -0.4495688480014975, -14, -0.4461722410678975] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1499  total reward: -4663.825329205428
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7619651603561477, -0.6952135081146882, -14, -0.44106480585413577, -0.4343775151105675, -0.38941616685243363, -0.46750245530818524, -0.42610045986092543, -0.42092124237354955, -14, -14, -0.42843162240059535, -0.4450596523378775, -14, -0.44901603080425917, -0.4210227185480372, -0.41755191121165647, -14, -0.420006513933972, -14, -0.4173783426353299] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1500  total reward: -4664.765559937523
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7770134794537583, -1.0897932727359132, -0.7198620151077721, -0.6092592504636161, -0.5535411436050646, -0.5647882585813981, -0.5387313853680151, -0.5783190072886628, -0.5508540580257544, -14, -14, -0.5630708530203216, -0.5815894491399966, -14, -0.5930864286791403, -0.5379999553253885, -0.519661755998389, -14, -0.553755150657746, -14, -0.5508145652424222] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1501  total reward: -4665.658310231758
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6442236457068655, -0.6314403729607622, -0.5419169936662517, -0.4166913543814899, -0.3941659095349254, -0.4032758408153012, -0.43657082018811316, -0.37971662113100557, -0.37901618627711714, -0.4130046316390893, -14, -0.38112978141982384, -0.3916633701660831, -14, -0.4096242751334561, -0.3758483898312938, -0.37625225845685545, -14, -0.37396418545414234, -0.3832473391195509, -0.37308853823717275] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1502  total reward: -4666.764614515638
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.667953657515899, -1.1973268266762305, -0.8786229902562952, -0.7403980829063542, -0.7727815632776243, -0.7816357230158515, -0.9026206180808443, -0.7463514511487301, -0.7412718917960451, -0.7604866799248718, -14, -0.7483153118845712, -0.7698512124661805, -14, -0.7851678021084991, -0.7362262785531842, -0.726011665983803, -14, -0.7350092217053346, -0.7585061374026144, -0.7332157456425363] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1503  total reward: -4667.990315765148
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8357743991430051, -0.8831956867364723, -0.7248333733613685, -0.5603474820674871, -0.5246944078407438, -0.5374607953407768, -0.5848123248912874, -0.5166596541365162, -0.5024236890149449, -14, -14, -0.5159700425397878, -0.540323776890202, -14, -0.5431389820787286, -0.5064646911949554, -0.5009866304620835, -14, -0.5035157902219449, -14, -0.49968958352641035] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1504  total reward: -4668.867884426916
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6155121726673529, -0.7162265351161812, -0.5051665714427536, -0.4309116812414777, -0.3938311784311785, -0.38621531195825415, -0.4222339007913204, -0.3855810352004338, -0.3820632571355387, -14, -14, -0.3910996129106954, -0.4126540878558033, -14, -0.40991933705026556, -0.3812834883511333, -0.3751217453431344, -14, -0.38157775497956925, -14, -0.3778790782424794] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1505  total reward: -4669.577551208866
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5861918555954068, -0.584172808521583, -0.4807784237083694, -0.3866640089649474, -0.35575137350759, -0.3504738067126647, -0.4026590972755561, -0.3374506068404198, -0.3399732052839809, -0.3657450364602575, -14, -0.34195194602379453, -0.35201853154944707, -14, -0.3604081416686161, -0.3368685508632984, -0.33341198629998703, -14, -0.33538830766809175, -0.3438985754500669, -0.3345450366062415] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1506  total reward: -4670.2108893718705
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.49082360936411307, -0.5611242557277922, -0.38800000974561055, -0.33751068259359585, -0.3123930959188694, -0.30491604347169904, -0.333507113593506, -0.30841775394556586, -0.3032212453981873, -14, -14, -0.31146234672398143, -0.32967437003477307, -14, -0.3301087163704673, -0.3027707016467038, -0.2975618534358526, -14, -0.30295239052463024, -14, -0.2999261767047918] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1507  total reward: -4670.914600814052
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7241883414691442, -0.6940749530724192, -0.5917675715932844, -0.46394635983680443, -0.4323993803694271, -0.43204421793363146, -0.49416774858751866, -0.4114743602645567, -0.4116207983209694, -0.43803589181852587, -14, -0.41444891655771365, -0.4257113391979894, -14, -0.43587372904952326, -0.40881111976815415, -0.40312839178952375, -14, -0.40696574910608513, -0.41809036424622836, -0.40614958874506096] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1508  total reward: -4671.7565694067325
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7340545568121438, -0.7960365231075712, -0.6135992725738448, -0.49403180919069406, -0.46011669369664326, -0.46117045749317825, -0.5068339095794284, -0.4462681400712432, -0.4448533715865493, -14, -14, -0.4537943544219861, -0.4762430224812109, -14, -0.47700067262345563, -0.4439460440725773, -0.43963684632881567, -14, -0.442380373396104, -14, -0.438840200891587] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1509  total reward: -4672.9441246969745
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9932571061530862, -1.492075231714664, -0.9016125269435276, -0.8192962424927595, -0.7401515015319917, -0.7502339791773256, -0.7118625105995822, -0.787914749503835, -0.7492206777545352, -14, -14, -0.7693501358364464, -0.8002124193494577, -14, -0.8134715211731071, -0.715564224551425, -0.6885593907261324, -14, -0.7535629419702443, -14, -0.7487150893504916] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1510  total reward: -4674.408069513745
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3803255498829463, -1.3087001334553767, -1.1145414233694695, -0.8823378019074418, -0.8250552473494115, -0.821689256076625, -0.9447693545490058, -0.7898283337974291, -0.785321173495493, -0.8244526862654908, -14, -0.7920148374053659, -0.8131105126530701, -14, -0.837232095550926, -0.7805853849100456, -0.7702932110610343, -14, -0.7765625583681536, -0.8089796568287186, -0.7753854260433776] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1511  total reward: -4675.959598340987
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.244121044207061, -1.4298763843604119, -1.0553763762949528, -0.8831076271953971, -0.8128119237327823, -0.8059922131164099, -0.8702019852265357, -0.8039516505912033, -0.7896286379488808, -14, -14, -0.81254572692639, -0.8621785607046641, -14, -0.8602691984811486, -0.7890286526195028, -0.7745244289878532, -14, -0.7895173039639022, -14, -0.7812356161811249] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1512  total reward: -4677.5666159971115
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4035156988135324, -1.439443812298909, -1.1516998184478138, -0.9613528193738881, -0.8808175998196682, -0.8586197203353454, -0.9821390336132096, -0.8418927883121453, -0.8508027542837784, -0.9318557286339806, -14, -0.8527941141161602, -0.8788148093371221, -14, -0.9234094350522634, -0.8390289767381763, -0.8382504303771848, -14, -0.8345559369256058, -0.8627400867098145, -0.8324932271363382] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1513  total reward: -4679.746290647886
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.129225858491483, -1.4859758752563221, -1.4271661943728289, -1.5622837265784297, -1.6278800588585045, -1.384095941819148, -1.356099329053029, -1.4181653909803686, -14, -1.3690210328958201, -1.4049961381004137, -14, -1.4354669643632962, -1.3562564322191024, -1.3375323033468274, -14, -1.3508943037768633, -1.3787155213270996, -1.3471814236384687] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1514  total reward: -4681.894453935334
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.261217114090293, -1.4976381652142223, -1.1252978899184702, -0.9152515204710459, -0.8395160701016768, -0.8465043602410744, -0.8825223538071352, -0.8406528014949299, -0.814373913645105, -14, -14, -0.8424702836872038, -0.8938605043033646, -14, -0.8819348983563251, -0.8148908052408663, -0.797464372989552, -14, -0.819362114357734, -14, -0.8106309841020457] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1515  total reward: -4683.56813545025
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5257338050796883, -1.5374635652204725, -1.2264094446999345, -1.0065971856009543, -0.9294687458241884, -0.9102815969424761, -1.0405905785607463, -0.8756913745047031, -0.8982093594030502, -0.980951368299671, -14, -0.8961432997814609, -0.921482744221376, -14, -0.9561170855930039, -0.8820702742642275, -0.8748908834680668, -14, -0.8780500432815385, -0.9072102899587571, -0.8762171419260479] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1516  total reward: -4685.239538562428
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3382109339811223, -1.4030499691378908, -1.128499887385641, -0.8706246381899623, -0.8329607591385384, -0.8635297954215992, -0.9042332560530513, -0.8301729824381923, -0.7995067740563555, -14, -14, -0.8235632855005095, -0.86766992113087, -14, -0.8698531785183838, -0.8058267077429837, -0.7937488654485484, -14, -0.8040813176233758, -14, -0.7965122287093293] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1517  total reward: -4686.721750056124
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.239339527221361, -1.1839276775126641, -1.0006668141641024, -0.7744415458818706, -0.7314398592126998, -0.739743596564274, -0.8260331688511423, -0.6938930852277576, -0.6991842983548977, -0.7566872715892965, -14, -0.7019190967501955, -0.7220033732829063, -14, -0.738884757414937, -0.6932848965412055, -0.6862853069312804, -14, -0.6904572907893233, -0.7048584313726464, -0.6884626282466553] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1518  total reward: -4688.012351904888
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.000398971223556, -1.1017433034666297, -0.8286836605089446, -0.6838940294013973, -0.6328870888163488, -0.627218330914999, -0.6949224853247608, -0.6210726841113541, -0.6103262368686331, -14, -14, -0.6255520377780731, -0.6588050287720238, -14, -0.6618741844252982, -0.6119208230437433, -0.6039875362310745, -14, -0.6097965693785214, -14, -0.6043165418339007] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1519  total reward: -4689.332175123889
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.275574450588597, -1.256003839733492, -1.0201208405440005, -0.8239805961054448, -0.762026506758362, -0.7488111243514803, -0.8647816282220276, -0.7107861465451574, -0.7338296637917963, -0.7919943311137826, -14, -0.7334879845408054, -0.7569429424024301, -14, -0.7671806849615078, -0.7196493599707742, -0.7122115734487416, -14, -0.7178163541377833, -0.7418344134449957, -0.7158356827704226] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1520  total reward: -4691.400028458203
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3335390348150309, -1.3372969067206495, -2.036819652450891, -1.4568853122331697, -1.369440855637944, -1.568769972593258, -1.4281403733060163, -1.0493102876944171, -1.8047002203478935, -1.6431454689100011, -14, -1.372356204398653, -1.39541420706371, -14, -14, -1.3766272911977788, -1.336277582136704, -14, -1.3575249849361555, -1.349137159308455, -1.3570671877687066] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1521  total reward: -4693.671662102315
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.2062169866933568, -1.9531505404688942, -1.903747795605849, -1.3624801895060117, -1.3003221103717169, -1.3869629914398125, -1.5163267990891303, -1.2510656117753198, -1.2308295660490882, -1.2585011206357213, -14, -1.2441611686503256, -1.2809553238825642, -14, -1.2935102231187663, -1.228056611190599, -1.2074623853392188, -14, -1.2261296462646847, -1.2612709459004934, -1.222323356417439] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1522  total reward: -4695.585080805498
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1970618500575567, -1.2674800967761028, -0.978266805308375, -0.7749420741937363, -0.7386837572042051, -0.7522844983224783, -0.8010067652763837, -0.7381417692725165, -0.7076284947417062, -14, -14, -0.7293243015651638, -0.763682283116558, -14, -0.7687388687196963, -0.7139404893403863, -0.7028853572355593, -14, -0.711254885386198, -14, -0.7059563178434669] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1523  total reward: -4696.939680883009
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1189131522913818, -1.1549513430148126, -0.9171755105894611, -0.7607390520504437, -0.6916230449158731, -0.6726245048108155, -0.7756000093402351, -0.6493841038127011, -0.6686338676276812, -0.7227209899451893, -14, -0.6667843700875254, -0.6886157648473931, -14, -0.7078425726713145, -0.6560639960942878, -0.6497487881437235, -14, -0.6539515645745253, -0.6746854712054865, -0.6517147202752908] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1524  total reward: -4698.1361542310415
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9423414820341722, -0.9667260044909366, -0.7513647973370627, -0.6381389101664316, -0.5808960822319865, -0.5599143507276588, -0.6631607624984913, -0.5491892984842378, -0.5555717985232125, -0.5895862231682457, -14, -0.5600076129452823, -0.5725859848733053, -14, -14, -0.5473107334201422, -0.5577451271768921, -14, -0.5488446458118017, -0.5613983142233305, -0.547089244219638] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1525  total reward: -4699.564646743288
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3844761217187542, -1.7505566174506957, -1.1296755118321409, -1.0122272693255454, -0.9093920121291544, -0.8858210041485558, -0.9315464291574624, -0.8880430440590261, -0.9200271482505317, -1.2869551110430477, -14, -0.8886368648058302, -0.8896151664579133, -14, -14, -0.8706801952272453, -0.9602899592387583, -14, -0.8814757614558851, -0.8839811473158482, -0.8814032680271332] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1526  total reward: -4701.065020349204
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.125361278419824, -1.0684769396725986, -0.8965076204202809, -0.7192304289495799, -0.6708248499888009, -0.6623323878430457, -0.7709546128790279, -0.6281159471146923, -0.6283196238187788, -0.6569821622492766, -0.653104214441168, -0.6440771105396119, -0.6563094816823287, -14, -14, -0.6286465594930316, -0.6404297284711915, -0.6396527868251035, -0.6318865775805631, -0.6380685816785302, -0.6296934106893627] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1527  total reward: -4702.229846581238
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9676996773542593, -0.8857993213352183, -0.7514546498451593, -0.5965401509424659, -0.5696064763376221, -0.5710031892529258, -0.6345026097594153, -0.5520136248726429, -0.5416485712077542, -0.5591746918510956, -0.5630960747261211, -0.5482442393619494, -0.5614389688954214, -14, -0.5826848032979973, -0.5325260689117389, -0.5387653482532776, -0.5493467957133477, -0.5384878175424435, -0.5485777243169686, -0.5367102849188815] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1528  total reward: -4703.208150732986
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7798286487819345, -0.7859167918668495, -0.6110187008882773, -0.5079699932239197, -0.4722435277761049, -0.4610308670826359, -0.5253275534071576, -0.4478790347121955, -0.45589583241632936, -0.5020608763024175, -14, -0.45576732956625043, -0.47056260691002055, -14, -0.4891453332699657, -0.4493177572356056, -0.4461727421856086, -14, -0.44744543399086284, -0.45506527169624356, -0.4457780828360409] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1529  total reward: -4704.00869022584
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6043705988796881, -0.6415606070519099, -0.4813427570766, -0.40650334018548945, -0.37419753867060906, -0.3640852031272112, -0.40815845007723156, -0.35331070865662706, -0.3652728605902554, -0.41601414754367355, -14, -0.36440007759410176, -0.3754879897171736, -14, -0.3908105195759271, -0.3574162882571057, -0.3613735767747687, -14, -0.35566950265460867, -0.3629028099116999, -0.35476141001817807] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1530  total reward: -4704.7953509033505
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7510325524769359, -0.8207916613788314, -0.6227053047009908, -0.524464242202672, -0.46152382125743463, -0.44282996431068156, -0.5285682393611179, -0.43579695582379274, -0.5438426070007177, -0.4838558131821189, -14, -0.448397825175914, -0.46294791897085397, -14, -14, -0.4320807573285044, -0.4330219194605367, -14, -0.4370188312862744, -0.4694269762840704, -0.4333499688531828] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1531  total reward: -4705.5561862925915
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3263197051661233, -0.3252714096942809, -0.42131685447897654, -0.37656861089825067, -0.3312713403210353, -0.330830187979109, -0.3361702311162939, -0.2532434761948411, -0.37367160969248825, -0.34671719833449727, -0.3349706838000902, -0.3358926931199504, -0.3401526883343484, -14, -14, -0.3268355696277781, -0.34547182437624685, -0.32828227031520507, -0.32913084798810266, -0.33096347210722443, -0.3287546319135643] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1532  total reward: -4706.432573132552
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.118798500382692, -1.080776516423138, -0.866662343436404, -0.7047749677574241, -0.6620095161761822, -0.6515151387952267, -0.7296961498246891, -0.6259783759124843, -0.6325130210083101, -0.6792045912186161, -0.6481593408648895, -0.6363314675692596, -0.651798503345358, -14, -0.6694837373385971, -0.6177890733096151, -0.630270290917675, -0.6350393603505524, -0.6255478424809688, -0.634632750248248, -0.6231433637645529] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1533  total reward: -4707.838966765106
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3986766343177977, -1.3559538781269316, -1.1407612647511471, -0.895558295046789, -0.8378259308971431, -0.839078710397744, -0.9470144859900728, -0.7960071418717932, -0.8013574416682536, -0.8655388244555878, -14, -0.8043440650646215, -0.8269920943301944, -14, -0.8506625943241881, -0.7943928329396052, -0.7850404242848293, -14, -0.7906452240960955, -0.8085677224980077, -0.7886045592453959] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1534  total reward: -4709.391114198418
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2697101532467525, -1.3803816900720256, -1.0534866090789086, -0.872126427196026, -0.8048550685178455, -0.7950159375043793, -0.8957019386661257, -0.7877847591407119, -0.7755680312626569, -14, -14, -0.7998184777105607, -0.8483358972929668, -14, -0.8423580185752402, -0.777430780091319, -0.7681800902074111, -14, -0.7746602025369426, -14, -0.7671070090267953] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1535  total reward: -4710.994442461256
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.304737631537202, -1.5113996565779622, -1.198746136306744, -0.9616681577392269, -0.87119069334093, -0.8772570122673541, -0.9460098768358478, -0.8657922421001397, -0.8427684310371862, -14, -14, -0.8643646666509733, -0.9086006945104631, -14, -0.9203588413513233, -0.846052119822383, -0.8342779623512521, -14, -0.8435392287569807, -14, -0.8362212538112296] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1536  total reward: -4713.161848068476
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7958025580433745, -1.5141068956520363, -1.3716061594563005, -1.3679324736450735, -1.4003511486743427, -1.3551770299765682, -1.3628671733198645, -1.9493261269569033, -14, -1.3432743580764614, -1.3497476185626511, -14, -1.5203257047034329, -1.335438051545995, -1.4148886180750775, -14, -1.3327423692714522, -1.3300807318391614, -1.3331276448683875] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1537  total reward: -4715.579652454524
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.964515128740969, -1.8701548096299851, -1.4862711954163894, -1.2681978052105933, -1.1631319154653208, -1.1128763752919641, -1.4660894888385538, -1.0782394473105614, -1.1402086084013128, -14, -14, -1.1023823138740154, -1.114348504256324, -14, -1.2162095452138084, -1.0898865876704582, -14, -14, -1.0884058670871495, -1.0549245454167422, -1.0877236542087987] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1538  total reward: -4717.982201474928
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8173134465410525, -1.5597186768619329, -1.3851166190518254, -1.3709024988302734, -1.4168736495618206, -1.3483731907543695, -1.3861191620887916, -2.0397650221931563, -14, -1.3600442783708901, -1.3664133614517302, -14, -1.508635820684466, -1.3490196689642076, -1.439746762443985, -14, -1.3470495232698028, -1.344829578576322, -1.347624474987191] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1539  total reward: -4720.2437328806955
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.604282678223968, -1.4973614522510705, -1.2645897224153462, -1.0652209640508843, -0.9782178696790882, -0.9435627181836136, -1.248047729230525, -0.902820829342502, -0.9770497974188896, -14, -14, -0.9274415259203502, -0.9337394296760767, -14, -1.0506768424326085, -0.9135221258175774, -14, -14, -0.9167142668078837, -0.8744151556598567, -0.9167018271922311] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1540  total reward: -4721.8659076483855
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2438768607371065, -1.319237565790939, -1.023200758916575, -0.8691770174438643, -0.7894779437361316, -0.765284771308378, -0.8714191390929897, -0.7577580766768514, -0.7635313363134933, -0.8569746171863277, -14, -0.7658160210292573, -0.7895736282955864, -14, -0.8319725398141291, -0.7540007647564683, -0.759299291806631, -14, -0.749986297551781, -0.7657508590392392, -0.7477596120299028] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1541  total reward: -4723.3324382472565
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.211785342561817, -1.2336797749083428, -1.0071289838751871, -0.8142863398882835, -0.7583100800628182, -0.7538887082207872, -0.8352978418070465, -0.7294211621070703, -0.7337950823136005, -0.8185672317791857, -14, -0.736016396475327, -0.7567965935884197, -14, -0.8017667172287039, -0.7247918899809368, -0.7232656084905447, -14, -0.720340604210484, -0.7311475755285125, -0.718770986840288] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1542  total reward: -4724.6875366141885
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.077281759119787, -1.1088822490652204, -0.9002375228574603, -0.7289335884390793, -0.6724778898136567, -0.6654245616320654, -0.7434174262342579, -0.6377018866020138, -0.6531754228870442, -0.7197552510363125, -14, -0.65025202686708, -0.6687937342464271, -14, -0.7035652704927646, -0.6406929779743437, -0.6366636655026828, -14, -0.6379201593123794, -0.6545117554784277, -0.6363273800919822] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1543  total reward: -4726.144510759206
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4358189094609533, -1.4581774079832177, -1.1543013952325083, -0.9480940410155192, -0.8713689089204766, -0.8513483892442655, -0.9764646618229924, -0.8203009577359303, -0.8393595915188871, -0.9311210734811645, -14, -0.8375293592650411, -0.8593192842051838, -14, -0.8883523936187971, -0.8262729597602321, -0.8208791847528404, -14, -0.8221845154836661, -0.8460057174993262, -0.8206467649257781] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1544  total reward: -4727.897143628925
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6334936452334547, -1.6628799027991745, -1.3037664252220822, -1.06905124795434, -0.9887203985435008, -0.9689740363775267, -1.1148677050960218, -0.9341894160005579, -0.9435279049576895, -1.0299014043262542, -14, -0.9525429379138096, -0.967684659798436, -14, -14, -0.9326529722179411, -0.95670556383744, -14, -0.93368943795005, -0.9477684513459784, -0.9323319119828892] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1545  total reward: -4729.832078557667
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6990428298437046, -1.7234079718291335, -1.4327917767166098, -1.1514052136878539, -1.0613608011080546, -1.0524677066736077, -1.2000728983355784, -0.9897639736969099, -1.002045287241669, -1.096197702500838, -14, -1.020570408413016, -1.0378557551317498, -14, -14, -1.0033058986357053, -1.0286221372377689, -14, -1.0044734279974994, -1.0081350119282204, -1.0026030167597217] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1546  total reward: -4731.846030966271
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.1738895749006577, -1.6022997532700198, -1.2317652061068491, -1.034918164711303, -1.0739500831558146, -1.097695296308063, -1.2335289616731717, -1.0824908383743308, -1.0311967433335036, -1.0516959672448394, -14, -1.0431187872713954, -1.0701579019682257, -14, -1.13909557307088, -1.0304588182238472, -1.0155979433379692, -14, -1.0262201743089627, -1.0590259270036098, -1.0241884349065478] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1547  total reward: -4733.599131793009
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.260191199435623, -1.3175405399537827, -1.0542724851232603, -0.8332617575971433, -0.7770790682194758, -0.7823275770608301, -0.8797433715415788, -0.7539742414347763, -0.7453299550607204, -14, -14, -0.7610125721829952, -0.7963490487680484, -14, -0.8017232685926355, -0.7477977109915083, -0.7422311698487899, -14, -0.743082951880749, -14, -0.7375028834000873] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1548  total reward: -4735.090213051613
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2859068232338313, -1.3738506482543098, -1.03524052568426, -0.8396195999030632, -0.7904516264801402, -0.790385405474486, -0.8676841914863694, -0.7634312851789893, -0.7661001956905382, -14, -14, -0.7798639771165962, -0.8232058636523708, -14, -0.8199832450570101, -0.7626423657361525, -0.7541952958543872, -14, -0.7610982759626257, -14, -0.753578375205032] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1549  total reward: -4736.581870900029
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2011887255352398, -1.3980426010731544, -1.0038020439464532, -0.8255193240837846, -0.7667542754168328, -0.7671785032145225, -0.8052723664600565, -0.7590947397242972, -0.7418440964377759, -14, -14, -0.7644742601257528, -0.8057300402702765, -14, -0.7937264352679876, -0.7424343250830491, -0.7261617531727754, -14, -0.7448655284906112, -14, -0.7380794732099148] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1550  total reward: -4737.97626021573
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1292551070535095, -1.1607239170322508, -0.9803079442444419, -0.7756637113779651, -0.7080722791560933, -0.7050259980218578, -0.7917449228922991, -0.6675403945904627, -0.6845305940241573, -0.7474980534387806, -14, -0.6831178339075682, -0.7026018930862493, -14, -0.7265399531860717, -0.6723163789039602, -0.6673033041111783, -14, -0.6697519209894275, -0.6911584167839423, -0.6682275625280133] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1551  total reward: -4739.185231921895
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9155832332571172, -0.9906635925206805, -0.7447276878395155, -0.605311682318761, -0.5675911255957009, -0.5671481367715081, -0.6205123147446837, -0.5552682873132064, -0.5456974922401138, -14, -14, -0.5635553665014332, -0.596107794130422, -14, -0.584841159033223, -0.5479958331946048, -0.5390351095797571, -14, -0.54675125277318, -14, -0.5416684020543311] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1552  total reward: -4740.1961235208855
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8407475669722895, -0.8182370311529511, -0.6528676318290937, -0.5241022108107092, -0.4990832367765139, -0.4983915402858329, -0.5518789079666161, -0.4772989661765804, -0.4810204473019666, -0.5345912256192968, -14, -0.4812169990132013, -0.49217212208014227, -14, -0.5190003889520782, -0.47554424296352715, -0.47288173350766305, -14, -0.47244476100457705, -0.48176468029971536, -0.471856489410927] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1553  total reward: -4741.046062383809
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.632392166272392, -0.6527055726083373, -0.5344170946050913, -0.42628693558360686, -0.39801577384825254, -0.39943095396267597, -0.43386995883980994, -0.38260665226850704, -0.38647881137874845, -0.43261794608568155, -14, -0.3872172239320974, -0.39799818771036116, -14, -0.4218615304730507, -0.3810527540761103, -0.3832502081193623, -14, -0.3789147402515424, -0.3855721159050441, -0.3780823735123626] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1554  total reward: -4741.76077164975
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.57892034859225, -0.5809486768788177, -0.453864483136673, -0.38015419682514645, -0.3556106437676661, -0.34769359297837477, -0.3933978287031348, -0.3375414648277107, -0.3464485389720859, -0.37784278925963205, -14, -0.3457547132916185, -0.3595719867359966, -14, -0.37673343784473556, -0.3390310083636934, -0.3393246929558886, -14, -0.33840173741205637, -0.34785159143533906, -0.33662689242780675] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1555  total reward: -4742.609521788429
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9275597071705333, -0.9222396020479899, -0.7342039369649146, -0.6298164909958462, -0.5523259439070993, -0.5203730249647773, -0.6603502761875262, -0.5075495346758884, -0.5368330290851139, -0.545706710609293, -14, -0.5272557065023197, -0.5510259233738657, -14, -0.5075495346758883, -0.508944298535197, -0.5070418082897318, -14, -0.514968415813271, -0.5564399581241554, -0.5121232462527763] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1556  total reward: -4743.687474643073
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9419329395825778, -1.022080068384114, -0.7907909129415273, -0.6356131068327988, -0.59677285411855, -0.6019639267305276, -0.6489395532925445, -0.5953094138554308, -0.5730213927743452, -14, -14, -0.592596561845224, -0.6281912837893492, -14, -0.6237225914518907, -0.5775414692970934, -0.567492704310336, -14, -0.5770594806686438, -14, -0.5709110463539445] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1557  total reward: -4744.948905275478
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2271456720585854, -1.2119768022196404, -0.981393270341512, -0.8037100771438852, -0.7389606788486345, -0.7209630106374535, -0.8417052324230949, -0.6971708888745384, -0.7068554007822754, -0.7580657268537769, -14, -0.7095863437896, -0.7319028329209345, -14, -0.7475081394483744, -0.6983379650841329, -0.6910780999794712, -14, -0.6959663905083556, -0.7193418305149417, -0.6939379280941069] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1558  total reward: -4746.431225325124
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2517583835031278, -1.4248616772236862, -1.093008381623482, -0.8889445411918302, -0.8228734126703148, -0.8278298490680722, -0.880129067949198, -0.8275152136877664, -0.7944011773530113, -14, -14, -0.8222399725270522, -0.8742314477069849, -14, -0.8698835799826138, -0.798551010637065, -0.7830122809851892, -14, -0.8004124252230895, -14, -0.7912419496662964] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1559  total reward: -4748.153175025036
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6049286474099338, -1.596315054925559, -1.3751060713629926, -1.0729262671838247, -0.9948135121869858, -1.00128613581633, -1.1159880911646425, -0.9524897670849297, -0.9542107114242511, -1.0270520498404017, -14, -0.9596377867386685, -0.9890619308224796, -14, -1.0242334257887766, -0.9457597606644885, -0.9394561523035655, -14, -0.9417555929913889, -0.9662474458103771, -0.9389374189273751] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1560  total reward: -4750.065307327944
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7148514318944859, -1.695659209388029, -1.3435526494090384, -1.1200762808863118, -1.0345459201632259, -1.004522497507956, -1.1712200278172327, -0.9791070149364033, -0.9938331358592097, -1.0742818738499726, -14, -0.9962708441879805, -1.0260701895933355, -14, -1.062312313199748, -0.9792013287572598, -0.971552986278037, -14, -0.9753580203803927, -1.011824626739555, -0.973194883979855] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1561  total reward: -4752.021978212693
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.647879012775173, -1.7453713915342344, -1.3911214403933183, -1.087118066595139, -1.0309934855035598, -1.0570512943555774, -1.125468492971307, -1.0324631388645233, -0.9871164706488273, -14, -14, -1.0193235642052039, -1.0715171756748498, -14, -1.074313985468507, -0.9970737597483564, -0.9818439703166081, -14, -0.9934919673101817, -14, -0.9851178984716393] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1562  total reward: -4753.966503826085
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5738503633720673, -1.6225455145338747, -1.3984757935698293, -1.1164718028310565, -1.0172142684364147, -1.0123419080370444, -1.1351781006645731, -0.9802651311640994, -0.9809901731599655, -1.0601743478575907, -14, -0.9869042433248306, -1.0171108869021714, -14, -1.0705195162642438, -0.9701570746557179, -0.9622775825502196, -14, -0.964966024161818, -0.9880251182683208, -0.9626816430743266] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1563  total reward: -4755.994450094167
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8089045023100512, -1.9630978312529366, -1.468993237906516, -1.1909023936281509, -1.1167652914604407, -1.1168469946166655, -1.2184640874385995, -1.0858271542378004, -1.0778511412204645, -14, -14, -1.0995210512075622, -1.1558144254103502, -14, -1.1541567825308006, -1.0778938092570154, -1.0644278755624945, -14, -1.0755162347177836, -14, -1.0656686855328723] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1564  total reward: -4758.056561959873
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7549745201509228, -1.6510123973162687, -1.46776235337383, -1.118544735733011, -1.0581659216203612, -1.0840615009643395, -1.2004037199752309, -1.0160606120179085, -1.0117160756983485, -1.067205317656801, -14, -1.0201598405990517, -1.046415682187137, -14, -1.0843595498230305, -1.0047321908065823, -0.9903760860066906, -14, -0.9989130550253107, -1.0291840117894324, -0.9976839901427365] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1565  total reward: -4759.751323775645
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1858465325863263, -1.2687232623910838, -0.9883831460062437, -0.8057382840697372, -0.7417591220335078, -0.7343652047847276, -0.8396827476499671, -0.7203361859933528, -0.711827765381977, -14, -14, -0.7305456624335335, -0.7673356235253476, -14, -0.7660404976142459, -0.7143964460740165, -0.7079175881357548, -14, -0.7097855347640311, -14, -0.704385729765154] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1566  total reward: -4761.199312048461
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2239030251993772, -1.364655385947296, -1.0161164724417864, -0.819562579540579, -0.7740298062073412, -0.7832242158264796, -0.8188757030143875, -0.7732691368152169, -0.7467515338688795, -14, -14, -0.7710112829601966, -0.8103044488764529, -14, -0.8111080490937468, -0.7498231058172476, -0.7355750849300382, -14, -0.7494958592034053, -14, -0.7436025430515545] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1567  total reward: -4762.664423101066
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1986957292029885, -1.2760451074904446, -1.0302999009301252, -0.8418793396022238, -0.7685893195757338, -0.7588528685598089, -0.8416187727296626, -0.7295523083473217, -0.751599869634349, -0.8303229381276124, -14, -0.7476900194014207, -0.768539732447231, -14, -0.8140662320032898, -0.7346279791697856, -0.7316735319290953, -14, -0.730918510883287, -0.7501823761238835, -0.7295359676744385] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1568  total reward: -4764.269809256064
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4737721537927053, -1.589316833850397, -1.1744605578438898, -1.0314066325179743, -0.9262558790079745, -0.8859522008037276, -1.025133230442106, -0.8685692343953334, -0.9053446048352632, -1.0218420716578391, -14, -0.8998858145669583, -0.9284383116594085, -14, -0.9654234604758414, -0.8822245413005468, -0.8799644558711162, -14, -0.8781099701064866, -0.8982217066346333, -0.8758501873240976] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1569  total reward: -4766.1824368739435
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8378331523075897, -1.8640064665706149, -1.478690323926511, -1.201289251734819, -1.1086449022732698, -1.088993598679698, -1.255996517979556, -1.0439351465137037, -1.0508490179123406, -1.1677746794920654, -14, -1.061623847270267, -1.0790092270215648, -14, -14, -1.043558952171897, -1.0726371765937563, -14, -1.0462165849078406, -1.0572804663699917, -1.044058383484393] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1570  total reward: -4768.020467294956
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3170657112095905, -1.3209642568432327, -1.2100316439345284, -0.9343494915179569, -0.844411832709115, -0.8475794332964798, -0.9663041118165873, -0.7901755281572475, -0.7916971794022809, -0.8186514631810203, -0.8283028871679751, -0.810725458042868, -0.8252844002651597, -14, -14, -0.7933520021223257, -0.8049630697084053, -0.8092563388434059, -0.7970479363028552, -0.8076138264050716, -0.7944714688400923] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1571  total reward: -4769.590963525952
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3989484950825712, -1.364929820149032, -1.075274350586293, -0.8809164098792964, -0.828165588101188, -0.8130693901620087, -0.9077466258514019, -0.7767925455797747, -0.7966542164777591, -0.8584987965307354, -0.8135456998577976, -0.7960741479731018, -0.8128286502955521, -14, -0.8440978324380625, -0.7746194851934987, -0.7877965518857823, -0.7962640416897804, -0.7823944549492352, -0.8001000256473132, -0.7803207028387352] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1572  total reward: -4771.114206438554
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3149425301807698, -1.2998101064167478, -1.0676678007836586, -0.8518204398852275, -0.7942029875491637, -0.7894382610526289, -0.8903505376608216, -0.7564664025591133, -0.761629984756216, -0.8352300574091706, -14, -0.7639206845566828, -0.782332381636918, -14, -0.8136853757217192, -0.7542569700504987, -0.7471835233829321, -14, -0.7496357849342836, -0.7666676454722205, -0.748623427408804] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1573  total reward: -4772.584862060117
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.217428318954735, -1.3329653198820184, -0.9900090715593289, -0.8102997947327054, -0.7574524686061103, -0.7545057201250702, -0.8243341469924892, -0.7374129154648729, -0.7323516661717491, -14, -14, -0.7505857905286233, -0.7899954419835692, -14, -0.7863550227309611, -0.7318692094620284, -0.721822841104281, -14, -0.7294738152459986, -14, -0.7234720981803867] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1574  total reward: -4773.893537002152
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9736810502636053, -1.0396135889567337, -0.8248172584417645, -0.6701341927462473, -0.6174074042930562, -0.6126458696798339, -0.6698217942515777, -0.5901869748410006, -0.6010920593950376, -0.6933730248989673, -14, -0.6001848179933411, -0.616550394361801, -14, -0.6510328630827236, -0.5914865507370232, -0.5995483603201466, -14, -0.5882846587922107, -0.5967792159899034, -0.5868521009296799] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1575  total reward: -4775.012837574123
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9182441649615748, -0.9127142257806534, -0.7540493640624998, -0.6035650648529801, -0.5635134038072303, -0.5611902655316096, -0.6280164444119404, -0.5359646839875671, -0.5447699786960716, -0.5919142076002529, -14, -0.5444700240458102, -0.5619051058925685, -14, -0.5872897002880744, -0.5360360920023245, -0.5325845357633402, -14, -0.5342501801668571, -0.5488004053746965, -0.532448471042244] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1576  total reward: -4775.9689757125725
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7264339470760812, -0.7538489847538364, -0.5789476054826637, -0.4948674581707416, -0.4493532606202496, -0.4324668924200107, -0.5028798694292106, -0.425257470015082, -0.4338657365719114, -0.4772199064289154, -14, -0.43328385750317966, -0.445503809772338, -14, -0.4654418281097846, -0.42674402884308815, -0.4230477897474548, -14, -0.42457809366394017, -0.4363329277876591, -0.4236896674070965] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1577  total reward: -4776.853300863365
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8417342063329243, -0.8780021382921203, -0.6454608438972625, -0.5624741460388745, -0.4952280200460196, -0.4667499635117581, -0.6143716006829942, -0.4628187698586223, -0.4859357087597981, -14, -14, -0.47489056565571264, -0.49461945624834874, -14, -0.4628187698586224, -0.4628366575563119, -0.4656752734198484, -14, -0.46427221077041714, -14, -0.4612773610444552] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1578  total reward: -4777.730967337624
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7028735993897701, -0.7199264587979597, -0.6099116852687572, -0.468574415528901, -0.4387053120203076, -0.44953535244032305, -0.5012362033600134, -0.43357726111722544, -0.4183763899543137, -14, -14, -0.42793769146868077, -0.44455504657271877, -14, -0.4563847023316506, -0.42267254454967335, -0.4199792170514368, -14, -0.4188917175420488, -14, -0.4163891132144836] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1579  total reward: -4778.648634454361
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8643399983336753, -0.9735736064550505, -0.6858123588290208, -0.6387596270225541, -0.5365460825841327, -0.5012023392130234, -0.6618985676762179, -0.5029647709177447, -0.5282616930949453, -14, -14, -0.5175343872740041, -0.5422554905674046, -14, -0.5029647709177448, -0.5036754350780401, -0.5069293093860222, -14, -0.505230208115358, -14, -0.5012780035225491] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1580  total reward: -4779.741651051598
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1123756077324658, -0.9897160022274646, -14, -0.6160441888830805, -0.6162213592877753, -0.5556030245721223, -0.6622856017736308, -0.6081872237493008, -0.5961984372548016, -14, -14, -0.6100817297313732, -0.6349641735970164, -14, -0.6417796977559685, -0.5973680817818354, -0.5915056932767369, -14, -0.5953336098206164, -14, -0.5918142580243851] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1581  total reward: -4781.229819696131
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5877570110611459, -1.5857527034512207, -1.4395976087036402, -1.033105599540526, -0.9820737846685585, -1.0564561823685195, -1.118607022827972, -0.9499162629902119, -0.9442989075537792, -14, -14, -0.9562178315955285, -0.9928705370541692, -14, -1.0133390449645638, -0.9442949706983789, -0.940832198053915, -14, -0.9385415341067018, -14, -0.932565619960845] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1582  total reward: -4782.993281797889
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4157048054692107, -1.4907507784047038, -1.1703134656176502, -0.9441488321741176, -0.8756811665605598, -0.8714598940328697, -0.9936077073519244, -0.8577776976593956, -0.8351737829666558, -14, -14, -0.8617075417810053, -0.9044694946895353, -14, -0.8994573997860528, -0.8431239881995382, -0.8341551044880542, -14, -0.8370783805462632, -14, -0.8308964817970947] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1583  total reward: -4784.83693966291
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7576461632321578, -1.806304882694492, -1.4655061030249628, -1.1791408315232896, -1.075541915412177, -1.0599742068102604, -1.2776972058951224, -1.0235270114724881, -1.0294101034380487, -14, -14, -1.0420164356041288, -1.0865414089175038, -14, -1.095305789887157, -1.0258946973628413, -1.0249144236932006, -14, -1.0198858466268572, -14, -1.0127613832232154] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1584  total reward: -4786.720743748711
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.420078333608484, -1.5386705142766017, -1.247355945799996, -0.9791011065374898, -0.9116956539515788, -0.9285451804066225, -1.003703583957267, -0.894102898598175, -0.8812254635414397, -14, -14, -0.9026557065850903, -0.9514233578356678, -14, -0.9579230105534638, -0.8820849523278624, -0.8723924962906994, -14, -0.8789566903305736, -14, -0.8710427025792743] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1585  total reward: -4789.0249902387195
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.2079939082613547, -1.5836725614244507, -1.5094095616948868, -1.6254254677624045, -1.7166000468437366, -1.4799362313242819, -1.4389166918148681, -14, -14, -1.4713061089687234, -1.52549956850484, -14, -1.5435980668370166, -1.4530925418215326, -1.4438332558108515, -14, -1.441260247211634, -14, -1.4332037874289858] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1586  total reward: -4791.406547811345
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5163591958033038, -1.7481004903681365, -1.3063706406856952, -1.0876820568062109, -0.9892799324964913, -0.9786022690948253, -1.0735794271094126, -0.9740435354503458, -0.9573157434261673, -14, -14, -0.9868963437356743, -1.0399716453671792, -14, -1.035564202385679, -0.9582890598024177, -0.9442599204563317, -14, -0.9559572968960953, -14, -0.9483537851959859] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1587  total reward: -4793.652094182202
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7309661228553341, -1.5048794569749089, -1.3350334259682817, -1.3184476590039755, -1.3615686495678125, -1.2988968240949186, -1.3413470075992937, -2.031844190135661, -14, -1.31341346120936, -1.3212581513948478, -14, -1.4581909886770923, -1.3013588911910243, -1.403176851946487, -14, -1.301095574065348, -1.2997586231252252, -1.3012864504008363] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1588  total reward: -4795.831968634961
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5074475314168534, -1.494293964961619, -1.2630628524580838, -1.0065887640556823, -0.9336271457284114, -0.929758322872424, -1.0641772560265719, -0.8742512935398483, -0.8827417731992249, -0.956030573434182, -14, -0.8983434156193143, -0.9152520656745546, -14, -14, -0.8814455833776501, -0.9026067201679804, -14, -0.8829336563545511, -0.8928512187614349, -0.8809776286648483] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1589  total reward: -4797.5192322083985
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.464251924145522, -1.4395385772445062, -1.1321033370037252, -0.9127852822208703, -0.8620101266784227, -0.854386127541926, -0.9576765029818417, -0.8099224884720473, -0.833432539863904, -0.9241029183850549, -14, -0.8289957631728961, -0.8512198795148589, -14, -0.8803166882045266, -0.8187430125582087, -0.8121815305119816, -14, -0.8150230949748636, -0.8332133229333192, -0.8130122798972996] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1590  total reward: -4799.019446546111
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.182213951469126, -1.2285799599119225, -0.9446314136097765, -0.7880986348106079, -0.7291719860760655, -0.712619087713637, -0.810504598509133, -0.6896229328788389, -0.6988644208881549, -0.7931253850886265, -14, -0.704794096340796, -0.7163015019789115, -14, -14, -0.6896989433305378, -0.7204839348771904, -14, -0.6916251365773644, -0.6952582487584268, -0.6902918492402506] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1591  total reward: -4801.295656554813
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.04344123286855, -1.5909295132631898, -1.660369501128141, -1.8208377499104995, -14, -1.6741696474754817, -1.5889815248875725, -1.5959430142579603, -14, -1.607086936164128, -1.6429620743080462, -14, -1.6859617161828124, -1.5936774400016185, -1.5663227680878133, -14, -1.5897460019389096, -1.6324247594950516, -1.5865870758227512] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1592  total reward: -4803.851624401873
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6298727192669635, -1.8234264505305728, -1.4119129343406467, -1.1258654487106756, -1.0360426906377622, -1.0423838228607711, -1.1334132063111737, -1.013909063157457, -0.9964599683447446, -14, -14, -1.0204404400206089, -1.0653454721795306, -14, -1.0650692779943691, -1.0003044809619075, -0.9880472443982966, -14, -0.996507863218981, -14, -0.9896450789726278] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1593  total reward: -4805.281993044972
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4656930689690495, -0.45878236937009165, -0.5615159362960965, -0.5466672804977868, -0.4323098187048183, -0.44111975152085403, -0.44122480126971936, -0.5338378102399932, -0.4452183171969424, -0.4435204269740682, -14, -0.4632709405026016, -0.4862637696190893, -14, -0.6104522918608625, -0.4441595434196247, -0.454445907342112, -14, -0.44492221570115337, -0.473036486568663, -0.4423213987009628] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1594  total reward: -4806.618015212677
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3536410016860307, -1.3102414124330097, -1.2488910599282754, -1.0449797618257326, -0.8536825286142407, -0.9258512919986917, -1.025763662002986, -0.9109521955650347, -0.9211288128130694, -1.0387677588839896, -14, -0.9244537869658851, -0.9544314396087727, -14, -0.9786997864367517, -0.9113529021040375, -0.8940788722916436, -14, -0.9060617867561136, -0.9337797055334299, -0.9037123489998068] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1595  total reward: -4808.13056722195
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.127455603848893, -1.1546602268197974, -0.908293490869448, -0.7514807462648335, -0.6963528961351079, -0.6827975231066168, -0.7691128337234058, -0.6666658143971327, -0.6730116712010094, -0.7471009055744959, -14, -0.6748914282317915, -0.6924383400775805, -14, -0.7313991225439942, -0.6639031961226692, -0.6615808440637732, -14, -0.659800634128159, -0.6725247790838039, -0.6588694806588369] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1596  total reward: -4809.597756097583
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4248225538907313, -1.3780432990973634, -1.168378240508228, -0.9130125083084306, -0.8575856061249745, -0.8634023692626346, -0.9658211996698668, -0.8192697309903655, -0.8210770230681461, -0.8864518284889824, -14, -0.824391443251003, -0.848161947435899, -14, -0.8780624521398374, -0.8140709197699455, -0.8064337635803396, -14, -0.8106132817767726, -0.8299726391546639, -0.80831939497483] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1597  total reward: -4811.132371028153
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2138793788332016, -1.292947813148579, -1.0533758678631533, -0.816822534816496, -0.7640477037259303, -0.7816623955175983, -0.8476598736287855, -0.7536447146449967, -0.7323744412337889, -14, -14, -0.7513845417512749, -0.7858208190299713, -14, -0.793822637870507, -0.7378770677461244, -0.730149030459462, -14, -0.7335457634310544, -14, -0.7281811669888484] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1598  total reward: -4812.428922554248
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9798516401328747, -1.0243787999651692, -0.7905317235440701, -0.6227116575938038, -0.5956915447697256, -0.6077588147152446, -0.6491606303953747, -0.5874916014352138, -0.5707947773981068, -14, -14, -0.588226797206002, -0.6203755971358061, -14, -0.6139973985647452, -0.5747012034868927, -0.5663629839398912, -14, -0.573849207709221, -14, -0.5683703591063494] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1599  total reward: -4813.693505245297
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6534766619862626, -1.22730644872816, -0.8138957042322461, -0.7457153293894901, -0.750618885759673, -0.7026276166124839, -0.9329948666184027, -0.6903532810507005, -0.720718870016703, -0.7161514461370686, -14, -0.7167724548128619, -0.747182476645568, -14, -0.6903532810507008, -0.6926502740913344, -0.6922558316595165, -14, -0.7017975799170654, -0.7600494044132369, -0.6982197071095619] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1600  total reward: -4814.789367881099
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6961663520552666, -0.6897656179673594, -0.5642233737593167, -0.4600510238155403, -0.4291646646024446, -0.42380569472368884, -0.4857755546224108, -0.39937477379782166, -0.40498432458678313, -0.4370924451744761, -14, -0.41302502864532425, -0.42044137780115703, -14, -14, -0.4055425469771803, -0.4203485147599231, -14, -0.4063179289814887, -0.4110231891377434, -0.4055093547500421] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1601  total reward: -4815.5651117744
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6507665438339856, -0.6770971503447346, -0.5187617007288672, -0.4363238201430951, -0.39884881520388105, -0.3864923646366153, -0.44320583159543664, -0.37439734162609023, -0.3869584057633812, -0.4342454232381396, -14, -0.38555949362456116, -0.39719592321604397, -14, -0.4104252015561176, -0.3789345733673586, -0.3778706773795583, -14, -0.37735196098693957, -0.3859328486111313, -0.3763691195038798] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1602  total reward: -4816.3075774290055
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6756078778650839, -0.6603608390011884, -0.5208612426638874, -0.4181317806907026, -0.39193181207137906, -0.38677235683391825, -0.44772230317871725, -0.3705543220479483, -0.3735175418778734, -0.40946179647962544, -14, -0.37524699626012264, -0.3813500460865627, -14, -14, -0.36826390212421395, -0.3739373565428717, -14, -0.3687184719834943, -0.3741774913070482, -0.3680683129789046] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1603  total reward: -4817.07907431337
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7058984882215523, -0.698022675072776, -0.5799710830391577, -0.46782866936066037, -0.42946727267430646, -0.42207155862944357, -0.4964014518057682, -0.39814661331021106, -0.40210970790859785, -0.4332512220607177, -14, -0.4101877569486254, -0.41592152668188714, -14, -14, -0.4039744923714534, -0.4091446300805465, -14, -0.4037330039971781, -0.4071173577376896, -0.4034285713863425] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1604  total reward: -4817.805564676687
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3315521251309968, -0.32930893748482465, -0.4359078793496493, -0.3759294188985492, -0.32792571821265104, -0.33453791322211474, -0.33174109593584444, -0.42980967196297026, -0.32749101890746796, -0.34495964379492444, -14, -0.34084568802043, -0.356889707503206, -14, -0.4375855689513214, -0.32940605465676914, -0.3301771928901319, -14, -0.33019777366967634, -0.35131561450900567, -0.3283437500062266] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1605  total reward: -4818.862975753093
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2323902369683217, -1.2211438252731635, -1.0478457227078217, -0.8159053525841268, -0.769380583486712, -0.7835983962938795, -0.8484296796611418, -0.7353178270071515, -0.7193768264226525, -0.8331492969787602, -14, -0.7468092511917777, -0.7740424208389414, -14, -1.050280463570854, -0.7356673948528452, -0.7222529646876399, -14, -0.7322198150948408, -0.7613492274686768, -0.7299200574993857] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1606  total reward: -4820.385982285805
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3453077052554892, -1.367836183631546, -1.1493362497325406, -0.9131130044971502, -0.8480708701164542, -0.8499287709012519, -0.9367586295643459, -0.8123430550910536, -0.8223095038774481, -0.8909057870763512, -14, -0.8250623734348002, -0.8497806807953258, -14, -0.8960972000961316, -0.8089301569358676, -0.8058215634398923, -14, -0.8053008245155168, -0.826782851886234, -0.8036297062885612] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1607  total reward: -4822.231411887488
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.213508693658231, -1.058239477653734, -1.097173615020872, -1.0829796805864735, -1.2482214235346512, -1.07746096125032, -1.0532694845432533, -1.1039166008681598, -14, -1.061731628707389, -1.090039441520867, -14, -1.1489963834768107, -1.0494461167162097, -1.0363159151179964, -14, -1.0441903849219865, -1.0677409418269297, -1.0417998953947378] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1608  total reward: -4824.151090171691
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4442088257328511, -1.599574506177695, -1.2589864419926724, -0.9951101809896555, -0.9234902843278828, -0.9368390699612701, -1.0055278537996484, -0.912657439134823, -0.8874334727433736, -14, -14, -0.9166726089930246, -0.9658694919162778, -14, -0.9551131064014499, -0.8931770254258516, -0.8787599799273463, -14, -0.8909864332668772, -14, -0.8833623690844558] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1609  total reward: -4826.1235550271285
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8475284260427334, -1.8632715328302627, -1.5635159131756016, -1.2492526102550285, -1.1565579455878021, -1.1523504703331369, -1.287764934905267, -1.097868764873202, -1.1233642147566967, -1.2246309438636553, -14, -1.1169586576574648, -1.1510986711802855, -14, -1.2158689339050202, -1.09994621017676, -1.090010013255609, -14, -1.0970885531074697, -1.1299012380937716, -1.0937048755108354] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1610  total reward: -4828.172018218418
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5525635733317122, -1.6947927464481727, -1.3697313442603882, -1.0840815805861295, -1.0032722070680362, -1.0159935750246254, -1.107542373286616, -0.9986958879310511, -0.9614798546991861, -14, -14, -0.995099856195101, -1.0553186324049977, -14, -1.0428734267954305, -0.9706067847070623, -0.9548819315536695, -14, -0.9688663054165113, -14, -0.9584531780335488] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1611  total reward: -4829.998651825686
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.453354138116219, -1.5346419466830221, -1.2414917687911622, -1.012465685470668, -0.9210139896667826, -0.9066480314059346, -1.0175393522877383, -0.878295203359392, -0.8904626756634103, -1.0005399033754014, -14, -0.8897364814791576, -0.9131981567187093, -14, -0.9582657740388357, -0.8787159727998548, -0.8786418165149359, -14, -0.8736426093370042, -0.8927716992524001, -0.8717516757135935] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1612  total reward: -4831.577996386602
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1914067837777602, -1.2331321787750449, -1.001281534041911, -0.8035805017644242, -0.7460863051578528, -0.7440759197759222, -0.8169490988839945, -0.7158948892548613, -0.7221259716487398, -0.8120061709825654, -14, -0.7220910039525684, -0.7405548759038028, -14, -0.7831459363554725, -0.7132321716310599, -0.7161503728681371, -14, -0.7090683937543225, -0.723028469938899, -0.7075928852029684] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1613  total reward: -4833.027860081384
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2965740013351894, -1.2885490057370141, -1.0460542235258101, -0.8452587371472775, -0.7869473392891677, -0.77785631085027, -0.8804801867199903, -0.7428248630210993, -0.7608804094848242, -0.8315352397763689, -14, -0.7575061250423725, -0.7808605626825734, -14, -0.8127931394927111, -0.7470764263437341, -0.7400646787063432, -14, -0.7447825821338048, -0.7650951063683, -0.7422708095783352] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1614  total reward: -4834.466328918905
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1204972845215329, -1.2339915950768832, -1.0022948855968128, -0.7833788977017563, -0.7290398630039117, -0.7465053243861502, -0.7930893501805141, -0.7344596898436272, -0.6991722827762676, -14, -14, -0.7235151718235928, -0.7623815786050991, -14, -0.7606022203412441, -0.7059267574743054, -0.6937160172892142, -14, -0.7047331097097648, -14, -0.6984041588156168] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1615  total reward: -4835.892874825543
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2455773820933964, -1.2912305132560065, -1.020427817774412, -0.8345666573619991, -0.7734187725040742, -0.7632665803773427, -0.8483222139433965, -0.7347062430422131, -0.7521842211134814, -0.8477629739136732, -14, -0.7499968604671515, -0.7706109128724076, -14, -0.8119573976061687, -0.738315674189861, -0.7376388808444989, -14, -0.7343901325447285, -0.7475005168250788, -0.7328298893483325] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1616  total reward: -4837.730862566104
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6636038542923992, -2.0921751000034208, -1.4741888805271648, -1.246218149167557, -1.1346732045478696, -1.13321425816882, -1.1502031666695776, -1.1143001893032227, -1.1340680541991583, -1.6733239002887002, -14, -1.1134624187521753, -1.1190810477837165, -14, -1.2554529007084432, -1.1044014880222093, -1.1874714767807448, -14, -1.1049851798403585, -1.1035434986549588, -1.1051578512133888] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1617  total reward: -4839.705283742248
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4657781332215027, -1.4801636580102744, -1.2125467096022353, -1.0371511817257648, -0.9273778475118304, -0.888825164923749, -1.1482794102595963, -0.8621757485315504, -0.919029370094685, -14, -14, -0.8823256114034881, -0.8916689146366208, -14, -0.9887522295017703, -0.8744682137867112, -14, -14, -0.8714100427998145, -0.8416822269423242, -0.8708776774884909] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1618  total reward: -4841.292442766207
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3149440637819085, -1.2599183040131843, -1.0597697148821497, -0.8380887255866242, -0.7904448913101956, -0.7923319101319446, -0.8906645172181026, -0.7543203001210395, -0.7592832065221702, -0.809727254489779, -14, -0.7636881802290386, -0.7869073045364378, -14, -0.815751046743381, -0.750318193513062, -0.7449133042414807, -14, -0.7472057653890082, -0.7739681870499757, -0.7454767970170829] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1619  total reward: -4842.649685188015
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9964724596459137, -1.1228572152110012, -0.8163201298976742, -0.6947582716341855, -0.639446666981724, -0.6273199192299809, -0.6948516590734947, -0.6252815010515299, -0.622421835413213, -14, -14, -0.6374003220893609, -0.6759063664923992, -14, -0.6774641664269906, -0.6195582440192475, -0.6112572195045409, -14, -0.6185493528030273, -14, -0.61232911756604] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1620  total reward: -4843.968831931263
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2364314736044704, -1.2245423401193498, -0.9763987549124117, -0.8005833588333435, -0.7495248727004692, -0.7377508885280399, -0.8351675987349148, -0.7184716092470937, -0.7213716229474016, -0.7883749691214161, -14, -0.7236152568556178, -0.7439995079154823, -14, -0.7822650031128138, -0.7131907540334997, -0.7097353265420642, -14, -0.7094797102351873, -0.727362421960084, -0.7078895237433334] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1621  total reward: -4845.335479415955
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1554461471422641, -1.1618654328592584, -0.8895502110467284, -0.758379883820476, -0.6992912351656787, -0.6740008561960271, -0.7853884972203949, -0.6556083704562733, -0.67837807569499, -0.7374910677646026, -14, -0.6766669721763251, -0.6993333236789467, -14, -0.7230306858290307, -0.6625892898492518, -0.6586696132079881, -14, -0.660599408127608, -0.6858725356768796, -0.6587579609488332] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1622  total reward: -4846.407244088468
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7135977823168563, -0.720510360228161, -0.5944308603980131, -0.47289232976865353, -0.440189758720192, -0.4397113511320108, -0.49415643062774783, -0.41400776355753616, -0.41806368770790114, -0.4609013600777608, -14, -0.423177562720826, -0.42960526161111223, -14, -14, -0.4158801034622206, -0.4289410477986778, -14, -0.416861689656919, -0.4212416134481841, -0.41615630205736576] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1623  total reward: -4847.110047447975
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4811386736007674, -0.49578531194572567, -0.4179860416740208, -0.3312150892776203, -0.304957707114276, -0.3052101278008803, -0.3372801560809792, -0.28991740548382505, -0.29597996611037203, -0.3226674497952869, -14, -0.2956780402991473, -0.30497403928229483, -14, -0.31876076993732105, -0.29078862527959237, -0.2906170518870097, -14, -0.2896688867774498, -0.2993760420680396, -0.28879559594967763] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1624  total reward: -4847.676897976366
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.49103357848276113, -0.49745082283687747, -0.3923948111852955, -0.32131048651973376, -0.29551370371391283, -0.2887704795503012, -0.33170352030759365, -0.27534562771293525, -0.28595096238576023, -0.3120457259935521, -14, -0.2846172074681844, -0.29350756933338146, -14, -0.2990841927102827, -0.2795476397635214, -0.27670980500526093, -14, -0.2788718534898111, -0.2861072315139505, -0.27805493244009655] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1625  total reward: -4848.204536941204
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.43931081547231743, -0.43956467151719564, -0.3517750639194492, -0.2857768084314067, -0.26708261547776424, -0.2639879500343924, -0.3004198070784825, -0.25110559314869974, -0.2537049767222708, -0.28110907573775673, -14, -0.25669253688588345, -0.26077173742305587, -14, -14, -0.25220319597393354, -0.2594145020925844, -14, -0.2527692257188861, -0.25467757685192843, -0.2522933371257797] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1626  total reward: -4848.725402532853
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.48033827133498125, -0.5036917557278173, -0.37435285476257046, -0.3307991401007181, -0.28926642116363993, -0.27195083378145213, -0.3353660660496006, -0.26871343867626024, -0.2871762293375117, -0.30427969602933413, -14, -0.27660198770099764, -0.28791488425264106, -14, -0.2687134386762603, -0.2687656374396026, -0.2673046336746625, -14, -0.2712767442104038, -0.2885900439861436, -0.2697599985005038] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1627  total reward: -4849.34752008304
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7720086051415678, -0.5958074006496326, -0.4232203916517932, -0.35895785901814653, -0.3734971167716243, -0.375580074910333, -0.440026632508479, -0.3717803704060031, -0.35560830871004706, -14, -14, -0.3642186734430452, -0.3791630474302464, -14, -0.3873283973410548, -0.3601953958199452, -0.358401347679056, -14, -0.35731231435752303, -14, -0.35481291651217395] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1628  total reward: -4850.009608329923
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5151075821757691, -0.5700145084952858, -0.4102913797567252, -0.34518458155768994, -0.32145238359565886, -0.3164327088729339, -0.3488364931178217, -0.3141899146286238, -0.3108329762260022, -14, -14, -0.3184933114618906, -0.3351780359377219, -14, -0.33528266318252026, -0.31056961484359313, -0.30650916179679805, -14, -0.3098805838200782, -14, -0.3072753303714882] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1629  total reward: -4850.901390068118
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8896882787418706, -1.1296518399063022, -0.7576964641615456, -0.6665056449185297, -0.6013833652940783, -0.5914704878846242, -0.6113512097657876, -0.5859542694232863, -0.6033529558143936, -0.8935443007675138, -14, -0.5906327319021393, -0.5941064262985729, -14, -0.6626476791072546, -0.5853964430454713, -0.6286049541509058, -14, -0.5851648561022389, -0.5842132761330276, -0.585272576398633] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1630  total reward: -4852.073977551138
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0497405079103195, -0.9859442391373457, -0.8610817786921757, -0.6882592221637038, -0.6297620743794052, -0.6183544163659768, -0.8055618445105484, -0.5801512692968321, -0.6194393511889811, -14, -14, -0.5944295498965211, -0.5979561453156901, -14, -0.6516415964728514, -0.5866142300804769, -14, -14, -0.5883770537585331, -0.5675357243325766, -0.5883742068861655] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1631  total reward: -4853.197293603513
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9607831970450044, -1.0694305190651243, -0.740516330073179, -0.7028487793362381, -0.5946778722555742, -0.5551198810806386, -0.6857619741581198, -0.5543446734135616, -0.590432467570603, -0.6336527637631741, -14, -0.5726203977659517, -0.5962981416144301, -14, -0.554344673413562, -0.5557805467752545, -0.5510122873646465, -14, -0.5585235097308386, -0.5889557976679031, -0.5557803280412623] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1632  total reward: -4854.434351554499
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.435292668941824, -1.1304695195027097, -0.7911496722882998, -0.6862026239812151, -0.7174520722316634, -0.721248082083294, -0.8098485350944279, -0.7474965158688054, -0.6850503410464518, -14, -14, -0.7080635560005495, -0.7410816410702569, -14, -0.7612664585004436, -0.6965349578749612, -0.6881671412927354, -14, -0.6912468664797704, -14, -0.6860456636214906] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1633  total reward: -4856.117575363751
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.0668385935955806, -0.9828732184005404, -1.0189890284704355, -1.0018525289679987, -0.9414779248100564, -14, -0.9991865833977529, -14, -14, -1.0188376472345595, -1.0491819281787913, -14, -14, -0.9792864560839465, -0.9522245005258302, -14, -1.0028466432992384, -14, -0.9981734682053315] argmax 6
Action chosen: switching off line 6
  Simulating cascading failure
  ok
timestep 1634  total reward: -4857.964271203422
 Simulation with line 0 switched off
 Simulation with line 1 switched off
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.3058060154987274, -1.5149239221531243, -0.9230049371975482, -0.9265100950743069, -0.7276176014970842, -14, -0.856723938913414, -14, -14, -0.9299629604865548, -0.9688785464220574, -14, -14, -0.8244510977850951, -0.8642325722465929, -14, -0.9116592874144046, -14, -0.9052179148618628] argmax 6
Action chosen: switching off line 6
  Simulating cascading failure
  ok
timestep 1635  total reward: -4859.259326875941
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9201301527733199, -1.0273189798293965, -0.7635875326939366, -0.6451617036708154, -0.5931585016584368, -0.5830613765428768, -0.649709328142875, -14, -0.5623794064493718, -14, -14, -0.5897164486305805, -0.6230255062780613, -14, -14, -0.5782155878089976, -0.5754722979161236, -14, -0.5726684125175194, -14, -0.5674380710221775] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1636  total reward: -4860.3149427358585
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8334906935067522, -0.909208059960144, -0.664027955551143, -0.5689784602316219, -0.5193501872474499, -0.5033829909334157, -0.5862044934718559, -0.5044553235048438, -0.4990410880354457, -14, -14, -0.5113930459004596, -0.540130581338436, -14, -0.5388020607698211, -0.5001633889509971, -0.4953720216627363, -14, -0.49802411209927516, -14, -0.4932364534674251] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1637  total reward: -4861.301861860058
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8167103490710044, -0.9236030516437982, -0.6680715204132833, -0.5686225702255122, -0.5173689678337546, -0.5048126112439996, -0.5700377627474084, -0.501701401784432, -0.5012212390762187, -14, -14, -0.5104503995231271, -0.5368400792019752, -14, -0.5385840465963528, -0.49979967069952064, -0.4944309504415497, -14, -0.4980540547237525, -14, -0.49368267073284083] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1638  total reward: -4862.1839063655825
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6364284077777016, -0.7192768494725199, -0.5123349609631376, -0.44047379225450184, -0.40557840613316626, -0.3963108319947101, -0.43965782691703836, -0.40209770818954005, -0.39136761924361363, -14, -14, -0.4026416313900764, -0.4226993946650194, -14, -0.4272826491558953, -0.3926635418682824, -0.38674702106646214, -14, -0.3913016827234503, -14, -0.3883618347913768] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1639  total reward: -4863.1009185810035
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9258084370468772, -0.9129908482035727, -0.7557341456719278, -0.6081129192482139, -0.5631765005210606, -0.5562967839069884, -0.6362780830725357, -0.532548716618865, -0.5420460422769775, -0.5794703615874729, -14, -0.5412437896533164, -0.5575888646165598, -14, -0.5787086632608189, -0.5332198746342423, -0.5262426655441832, -14, -0.5318172603730165, -0.5490441817532273, -0.5302651943547906] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1640  total reward: -4864.149064776339
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8420393446764909, -0.9643281790949954, -0.6980830392674668, -0.5844064235860822, -0.5427084899630452, -0.5387621863133372, -0.576027642055293, -0.5383829470395392, -0.5267038537821522, -14, -14, -0.5428284825635558, -0.5722765329215173, -14, -0.5738677475975617, -0.5264413599407582, -0.5170117768037658, -14, -0.5262291263220524, -14, -0.5219035297910065] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1641  total reward: -4865.256710234129
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0122241177140017, -1.0127456056889275, -0.8565394493592595, -0.6675933944658592, -0.6243879124971841, -0.6314588558650255, -0.6917308703618938, -0.595069041984109, -0.603260259394129, -0.6605531219933127, -14, -0.6026560060182912, -0.6177971332377278, -14, -0.6485889551536516, -0.5948702177026086, -0.5898179770496507, -14, -0.591672775123318, -0.6056300757465765, -0.5906336809858798] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1642  total reward: -4866.362167188274
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8628820472741242, -0.9359927410658969, -0.7130616995627528, -0.5844870607646129, -0.5412547773872052, -0.5367816555834711, -0.6009170597808863, -0.5311281255842734, -0.5197245913627169, -14, -14, -0.5338657274842271, -0.5619920511379206, -14, -0.5626369460323922, -0.5225950140811673, -0.5161007896117501, -14, -0.5202048004074413, -14, -0.5156389770958582] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1643  total reward: -4867.30202206859
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6917939924449606, -0.8008511944690068, -0.5551431138068851, -0.46842097410649186, -0.43985453278109515, -0.4368189847877549, -0.4569732337482811, -0.43717634580270454, -0.42663760942000306, -14, -14, -0.4421833152788189, -0.46876136932028684, -14, -0.45901131100323395, -0.42590135855440503, -0.41500331895140824, -14, -0.4283416716725876, -14, -0.42421590321956515] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1644  total reward: -4868.360599334379
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1813310551671097, -1.0538214830925383, -0.9808593087228802, -0.712734311815186, -0.6844076907565739, -0.7237486549600372, -0.7894585892117003, -0.6538889074483804, -0.6496699563212823, -0.6746998326176601, -14, -0.654033308293428, -0.6702347537683853, -14, -0.6815682134516892, -0.6470997346064528, -0.6363950537776741, -14, -0.6449038171360495, -0.664561837006157, -0.6435739468380015] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1645  total reward: -4869.430998043971
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7037868830845462, -0.7875708933860165, -0.601486859626052, -0.4967024465321891, -0.4542262589841476, -0.44973786631980184, -0.5004389809774796, -0.4445847726945146, -0.44031253076217436, -14, -14, -0.44930916601967513, -0.4715698960058651, -14, -0.48013110252665536, -0.43960216849977224, -0.4352689888761382, -14, -0.4373961379624776, -14, -0.4340036558144521] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1646  total reward: -4870.203268502923
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5859017882361224, -0.6003375097050775, -0.492152927981992, -0.3817565313772812, -0.3572013481296072, -0.36262909283222144, -0.40922877349411696, -0.3470294080426241, -0.33993380066063494, -14, -14, -0.34920704164194616, -0.3673604986433988, -14, -0.3619326168413007, -0.3432504625012478, -0.33993267563714313, -14, -0.34143582721234533, -14, -0.3382668031364135] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1647  total reward: -4870.863354020792
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.561932327529579, -0.5466003986189116, -0.4935432059452393, -0.3571629282688373, -0.34004882104013756, -0.36236355905408396, -0.39526231758289826, -0.3297641701967732, -0.32394526729863954, -14, -14, -0.3315920939226725, -0.3441088703424473, -14, -0.34606154267013683, -0.32624463821024724, -0.3249163685190666, -14, -0.323460669802876, -14, -0.3218187147329668] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1648  total reward: -4871.496317226147
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5403354805257912, -0.5257242842044336, -0.4770966270124726, -0.34286636681819804, -0.32818240616788474, -0.352987523036669, -0.37783195987966933, -0.3222255135704038, -0.31226184393176803, -14, -14, -0.3187511159863071, -0.3302872003021507, -14, -0.336033411724478, -0.31562922287133127, -0.31392013439028665, -14, -0.31298353041373544, -14, -0.31114449062200217] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1649  total reward: -4871.999283645773
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3209311767460663, -0.34923612681891014, -0.2705319375309125, -0.2171255875361771, -0.20128282676156012, -0.201682242027578, -0.2226366793695324, -0.1971354183027569, -0.19318943175104103, -14, -14, -0.1986881062280402, -0.20964840473497684, -14, -0.20779503786687759, -0.19431017251180843, -0.1917659761278478, -14, -0.19366360712526398, -14, -0.19182192900438488] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1650  total reward: -4872.372377517826
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3028960877104522, -0.31602919201439544, -0.26511539316437427, -0.21101169417623572, -0.1918733190993251, -0.19067332286587282, -0.21351759116515084, -0.18383640951665417, -0.18428157445107476, -0.2037590351240873, -14, -0.18500172056092767, -0.18988129696754946, -14, -0.19781180051865832, -0.1828095347587591, -0.18180315408657172, -14, -0.1817249883422416, -0.18481055680750946, -0.18132789592520093] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1651  total reward: -4872.7497105451675
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.33343689946752236, -0.35097288556988204, -0.2669675890186664, -0.22431932165792975, -0.20680299205345362, -0.20163053888504298, -0.22612680233520036, -0.19508531423138722, -0.2023856800939403, -0.2285809304121047, -14, -0.2003952145072782, -0.20644943663845883, -14, -0.2176963185806029, -0.19727467651768235, -0.19790078238805037, -14, -0.19662408533773765, -0.20169609756213985, -0.19600513141610598] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1652  total reward: -4873.37472184167
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8025754092857913, -0.7095956412479184, -0.6373998787135482, -0.47495711796652484, -0.45758672076510715, -0.47605183293222997, -0.5365707737453812, -0.4210295194740354, -0.42923555042788997, -0.44794780876912954, -14, -0.43553917369460127, -0.4411158305713139, -14, -14, -0.4312741950982415, -0.4325881126039615, -14, -0.43017338213260686, -0.4332424145624236, -0.4299259822720685] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1653  total reward: -4873.960225155886
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.16999760563474414, -0.16854621390730837, -0.20236586044892568, -0.19641057851707622, -0.1621962344128699, -0.16402251584026264, -0.16476743764255353, -0.2011847360165907, -0.16527974353222663, -0.16630857480288075, -14, -0.17332490707011844, -0.18354193359925783, -14, -0.22829897334430027, -0.1652672346939651, -0.16728292983964055, -14, -0.16578362313884482, -0.17378021180310377, -0.16447379474230245] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1654  total reward: -4874.736634524081
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0647486547879623, -0.8849913729318921, -0.7444156346719613, -0.6517520909889563, -0.582084002890976, -0.6337245681274235, -0.6962950517600824, -0.6322513519062867, -0.6198528951508365, -0.633792606198557, -14, -0.6250720669563128, -0.6445973855120629, -14, -0.6616724731766996, -0.6167979002280888, -0.6058356053948589, -14, -0.61640015889214, -0.6422019946668512, -0.6142131337802713] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1655  total reward: -4875.800750910492
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8628347310329966, -0.8582761509203615, -0.6644643307785643, -0.554157649861146, -0.5127506568502398, -0.497237545022308, -0.5782836261446181, -0.48008518692542923, -0.4940367878196776, -0.540686432354278, -14, -0.49325204911913845, -0.5076546139118493, -14, -0.5207610351585942, -0.4849957353100372, -0.4802425843730767, -14, -0.4831205758994914, -0.49699488676072034, -0.4820323835207772] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1656  total reward: -4876.754662138963
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8089679952974267, -0.8439138288679192, -0.6585117693749983, -0.5484688791306734, -0.5016027606854925, -0.4887085139782389, -0.5637952492677791, -0.47700307423812305, -0.4853174151438958, -0.5297806370617418, -14, -0.48440474528659283, -0.49430980250626977, -14, -14, -0.47394918479314396, -0.48514025357582286, -14, -0.4753360492189995, -0.4811098354442515, -0.47382604154540797] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1657  total reward: -4877.72548571634
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8692007101165523, -0.8620920551380172, -0.7037512722677831, -0.5758056367240534, -0.528833414267883, -0.5167420198656544, -0.6105507086610202, -0.4955739487908765, -0.49870826512072236, -0.5334973308570309, -14, -0.5075127672673, -0.5179768628375702, -14, -14, -0.4975938198551652, -0.5074473861066807, -14, -0.4982250628152504, -0.5086838692648299, -0.49699753583165934] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1658  total reward: -4878.708544582052
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8152209483157238, -0.8467880149693545, -0.7065306389245913, -0.5751821616147476, -0.5172502086923326, -0.506568504373514, -0.5830680437949188, -0.4882450013373528, -0.4990283792393318, -0.5367950612244736, -14, -0.4981714205878637, -0.5144313299751434, -14, -0.5316115565164167, -0.4903101982100897, -0.485670399908014, -14, -0.4891803742419147, -0.507440542279961, -0.48748491692079704] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1659  total reward: -4879.669097336953
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7548923694630748, -0.8756556553054285, -0.6295178443386317, -0.5368338460219599, -0.49351734328351193, -0.4861840040831988, -0.5257018802659366, -0.49296618966528316, -0.47856345883261897, -14, -14, -0.49226952914355215, -0.5204510158614507, -14, -0.5248511200230853, -0.4788629821317611, -0.47068340865741337, -14, -0.4796902485334362, -14, -0.4748823549941941] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1660  total reward: -4880.661573230827
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.79681849151599, -1.0050818113707247, -0.6819064264181921, -0.5962737592713879, -0.5370667521085685, -0.5281853440475309, -0.548171739618924, -0.5263128285246418, -0.5342424523933191, -0.7857552270109343, -14, -0.5262741757756247, -0.5293861183571287, -14, -0.5876147394203165, -0.5223995666735103, -0.5650424034531975, -14, -0.5217169164880233, -0.5207551814267392, -0.5217924852160187] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1661  total reward: -4881.551782936185
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6574591462325897, -0.6330924790900571, -0.5266855121148241, -0.42720379788081775, -0.39395420920082913, -0.3861253008488903, -0.48689918903998775, -0.36637090488117185, -0.38641150680026526, -14, -14, -0.3749375448649171, -0.3793729003659854, -14, -0.41088152195098193, -0.3708602292246867, -14, -14, -0.36970075410090575, -0.36057899719433884, -0.36945452393093914] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1662  total reward: -4882.250877131777
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5813114228322943, -0.6144709839155825, -0.46196769243707164, -0.3909258975281201, -0.3578859908280113, -0.34687298439034536, -0.3935455762787421, -0.33606453036881045, -0.3487862712001083, -0.39625084576575553, -14, -0.346745092238928, -0.35705173849029714, -14, -0.3700026071808291, -0.3410480046644501, -0.34125876268058875, -14, -0.33942928053409116, -0.34594843053901164, -0.33851519839864647] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1663  total reward: -4882.962080415213
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6411339599489347, -0.6617554052095249, -0.5545498694534667, -0.43513389794462665, -0.39780526159805474, -0.3974003306839501, -0.4502222576288954, -0.3778301165211495, -0.3824820683043733, -0.4116551124247836, -14, -0.38388612746623924, -0.39171107595405164, -14, -14, -0.37532628410974445, -0.38261809812942554, -14, -0.37618421817918696, -0.3823402858325407, -0.3751387530657271] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1664  total reward: -4883.774734446011
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7610829098716537, -0.751739866163942, -0.6003879848225763, -0.5025178603537318, -0.46456235350346325, -0.45125330061433316, -0.5329717238746909, -0.43054839906478803, -0.43654013791719537, -0.4699540046769786, -14, -0.4469059060723825, -0.4552437625033174, -14, -14, -0.4382156849954413, -0.4498759202199458, -14, -0.4382341128494682, -0.4418367315521582, -0.43751527773277493] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1665  total reward: -4884.784222533709
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2804452443284038, -0.9257397262309764, -0.7089662526171417, -0.5855379907646843, -0.6091639559887208, -0.6262022110726723, -0.7097996323222459, -0.6042724219596928, -0.5816229133972883, -0.5956173946804189, -14, -0.5895943873113358, -0.6045564059323632, -14, -0.6234790131249305, -0.58264210596421, -0.5748847309276789, -14, -0.5800196595572181, -0.5970175486976836, -0.5789396886332939] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1666  total reward: -4885.796907977638
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7451003712880417, -0.7932537768383262, -0.6132246889056303, -0.4828976276317814, -0.45848812276361195, -0.4673197242174292, -0.49833594430328454, -0.44852976025823016, -0.4413976667609367, -14, -14, -0.45215725076631635, -0.47535013541870114, -14, -0.47361976814305595, -0.44269969865379977, -0.4365789567640853, -14, -0.44174464839096, -14, -0.43780071300085927] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1667  total reward: -4886.604475754042
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6616758098733544, -0.6385296155047034, -0.5103265006592621, -0.42147478963831514, -0.394233347676488, -0.38523112151255834, -0.4468187218789554, -0.37447829547852873, -0.37858473449585245, -0.4065927014407701, -14, -0.3791853030597683, -0.3903677805183803, -14, -0.40672838120672766, -0.37348968731215537, -0.3682700123792858, -14, -0.37188084405389193, -0.38230443430343447, -0.37098881964073926] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1668  total reward: -4887.394475791131
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7322080280230584, -0.770673058424359, -0.5897396319267539, -0.46545514670986454, -0.44264728733117825, -0.449391934973712, -0.48459936354442434, -0.433073727059643, -0.42412377551015773, -14, -14, -0.4350376270123747, -0.45433695297419385, -14, -0.4534663382947669, -0.42660777186014115, -0.4212435018552724, -14, -0.4246618990169926, -14, -0.4217300247093786] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1669  total reward: -4888.2301533250065
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.725764401711951, -0.7145379385191886, -0.5906158431300017, -0.46745813852376716, -0.4389413514864063, -0.43963497622385617, -0.4893645425560462, -0.41876051324086877, -0.42190851042317296, -0.4668653846123616, -14, -0.42336665867022183, -0.43351621857516415, -14, -0.45197467385618734, -0.41777070763797164, -0.4154193339276239, -14, -0.4149370516182062, -0.42404504077923966, -0.41443403202005863] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1670  total reward: -4889.390843899235
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1576004924020065, -1.453821874063248, -0.9812363207939708, -0.8606194461246803, -0.7704358534208301, -0.7542297554348902, -0.791570363722356, -0.7462860554909213, -0.7668271004078264, -1.1243420027359212, -14, -0.7524326279265467, -0.7570176033941389, -14, -0.8303623467595082, -0.7480618325604645, -0.7950051392629022, -14, -0.7461571312963515, -0.7444794215903594, -0.74625654220814] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1671  total reward: -4890.5763866291545
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7849721793241193, -0.7315751404497662, -0.6239878176494957, -0.5102428213522032, -0.4709827302744142, -0.45966693530830405, -0.5976850189872339, -0.43803398807266886, -0.4628461400399728, -14, -14, -0.44680407427927726, -0.450676197924866, -14, -0.4981707540626877, -0.43937366062432676, -14, -14, -0.44116196745947117, -0.4248152043887583, -0.4410633083296315] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1672  total reward: -4891.4164966223825
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.740294406301926, -0.7242879087257779, -0.5758360640687696, -0.4783543860963551, -0.4421776854677331, -0.429235659684689, -0.5035092496270899, -0.41196352940773767, -0.42767265897498724, -0.4521611181945996, -14, -0.4240489069251954, -0.43867528724667926, -14, -0.4511399182201375, -0.41672100834236453, -0.4109567164732142, -14, -0.4169994746228706, -0.43494937766493763, -0.41529478883899623] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1673  total reward: -4892.173836515951
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6146709581966551, -0.6685762759081226, -0.48102481169752737, -0.4290795190328492, -0.3708990780531176, -0.348418450501029, -0.45449548401261997, -0.3476270714077286, -0.3662821021471204, -14, -14, -0.3568604463937217, -0.37239496195224103, -14, -0.3476270714077286, -0.3474344833938655, -0.34986906825232944, -14, -0.3488007029673803, -14, -0.34638317709571836] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1674  total reward: -4892.8283583832535
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.48801804572517643, -0.5706758994423932, -0.408788949119567, -0.3454657862274973, -0.31946335215961913, -0.31677220287935487, -0.3359154251589008, -0.31915358172345265, -0.31050409006165136, -14, -14, -0.32012395981407826, -0.33958122796804885, -14, -0.3391437495093543, -0.31041721304435277, -0.3034976816269797, -14, -0.31146347538195024, -14, -0.30813869020648715] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1675  total reward: -4893.46952173134
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.582579327591768, -0.5993950816315499, -0.4646917676564899, -0.3838887502608136, -0.35677543969973224, -0.3501586014561314, -0.3921746589547192, -0.3378992963863831, -0.346533006973235, -0.3931902081329153, -14, -0.3452868152765114, -0.3555068337307393, -14, -0.3720972229365509, -0.34022900009242185, -0.3413995740874454, -14, -0.3386623146793714, -0.3451154542521329, -0.33766566645965285] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1676  total reward: -4894.389171362226
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0024396219372922, -1.0065179009899872, -0.8386415361114268, -0.6704921870126364, -0.6174743094630231, -0.6118493102752867, -0.6941443271156253, -0.5873317973379257, -0.5930794308115683, -0.6399581670943444, -14, -0.593886921977076, -0.6111826236306852, -14, -0.6347819578775372, -0.5856696217603296, -0.5794986523187259, -14, -0.5835942395468983, -0.5991074526499538, -0.5819839644265066] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1677  total reward: -4895.685507006812
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2018741107936215, -1.2084378165950107, -1.1058477074251072, -0.7941957639220727, -0.753828981117505, -0.811948999377719, -0.8551268415190967, -0.7469162249056237, -0.7182380285480015, -14, -14, -0.7395346887312544, -0.7746257383876256, -14, -0.7744174170331402, -0.726974308542601, -0.7207309444087214, -14, -0.7225444353702034, -14, -0.7168369922678146] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1678  total reward: -4897.463698965248
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4157892332024904, -2.1250527074823924, -1.332548243207686, -1.1831101307589968, -1.0525866372043469, -1.0693978454449584, -1.0200952096225184, -1.0938162655102301, -1.0654350742004426, -14, -14, -1.0909229659121875, -1.1339692523549805, -14, -1.1386265682317633, -1.0217368563249642, -0.9823803588936263, -14, -1.067922125733499, -14, -1.0613549661678863] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1679  total reward: -4899.288397971998
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4137961298888897, -1.4736272623624804, -1.2027692523685893, -0.9762268544928885, -0.8908371860438464, -0.8782818235665543, -0.9885860150933078, -0.8442974244577048, -0.8624054413876584, -0.9569580041079968, -14, -0.8619254448457467, -0.8884283305180745, -14, -0.9226748499207384, -0.8486406999091979, -0.8507183214853217, -14, -0.8447967856222359, -0.8702760906249568, -0.8423186478562777] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1680  total reward: -4900.981393624144
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.475554788809206, -1.4641458600105957, -1.2072747541268654, -0.9652901125016052, -0.9009588254481452, -0.8967931368782202, -1.0058081290937142, -0.8653247375430043, -0.864576809264212, -0.9337739464212983, -14, -0.8696719797323507, -0.8944755586127858, -14, -0.933666170866705, -0.8566298999149435, -0.8528998086896707, -14, -0.8526505545220213, -0.8753276841344471, -0.85067700429049] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1681  total reward: -4902.931429569084
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9336438011696944, -1.7761401381721835, -1.7229236809673398, -1.2251463877840867, -1.1661885667613823, -1.2522286757175687, -1.3322363146205178, -1.111067195293176, -1.1138187058096927, -1.1552245491419808, -14, -1.1222452684986979, -1.1562692741692322, -14, -1.1728453862543256, -1.1046800385360032, -1.08943002274618, -14, -1.1025572813133484, -1.1383997157025179, -1.0993589406489053] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1682  total reward: -4904.515778957067
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5095363885589105, -0.5045526900490788, -0.6244386047418471, -0.5497933367013215, -0.4891019238766966, -0.5044327157794211, -0.4954609305836803, -0.6724975284798779, -0.4938278823370929, -14, -14, -0.5217626988910163, -0.5646649372224881, -14, -0.6574410442031936, -0.49843596668334506, -0.4908904267753619, -14, -0.5021372287028089, -14, -0.494919365236117] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1683  total reward: -4906.186127270782
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7729635401922503, -1.6898988399269175, -1.8065036073367138, -1.319999852082475, -1.1214778081323469, -1.3158749915767, -1.3527935403366145, -1.218429586675754, -1.1837262266209534, -14, -14, -1.213056676110717, -1.2627960257127286, -14, -1.257306639797988, -1.2017309477069942, -1.1970876778532495, -14, -1.18943108236168, -14, -1.181246389838532] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1684  total reward: -4907.951604148446
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.036807009093726, -1.193889117230156, -0.8936993999920271, -0.7320074276900762, -0.6711814692460009, -0.6697440194116283, -0.7217156427702509, -0.6578914172512854, -0.6525309539913701, -14, -14, -0.6672993244123991, -0.701708693939472, -14, -0.7054885978306058, -0.6507674139243573, -0.6422200964873072, -14, -0.6493309242037664, -14, -0.6439990695318746] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1685  total reward: -4909.321719440306
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2288681482925237, -1.2624653687517202, -1.0369945799201015, -0.8382233093339247, -0.7699647608889842, -0.7612876246951232, -0.855744832940719, -0.7370559961003642, -0.7419874249795526, -0.8212251691488676, -14, -0.7425186174613396, -0.7625257841093684, -14, -0.8016564946505194, -0.7336703563924009, -0.7299689750760217, -14, -0.7295928028224027, -0.745811537073203, -0.7278951953728657] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1686  total reward: -4910.950443677995
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7240947574636596, -1.6605696904636347, -0.9760255278719611, -0.9099020181926316, -0.9374868692760054, -0.9013141215447121, -0.9440371951815426, -0.931945218703182, -0.9121318911774852, -1.2953005097143904, -14, -0.90761270450832, -0.9101796815312594, -14, -1.022315834010141, -0.901993367784658, -0.9727856717282587, -14, -0.900361550907613, -0.8995330581225445, -0.9008290423159432] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1687  total reward: -4912.521361512898
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1831371256765943, -1.1366835687537162, -0.9206136417744778, -0.7884945022737677, -0.7173287276084516, -0.6857912290502989, -0.9065782353086577, -0.6621817535316735, -0.711705709651301, -14, -14, -0.6799604081961336, -0.6874822068550432, -14, -0.7612519152485299, -0.6692913803196375, -14, -14, -0.6719023354632493, -0.6474328400493661, -0.671384776779871] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1688  total reward: -4913.996982721859
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4122870671384087, -1.4511257229991292, -1.1788750723150447, -0.9560506507986917, -0.8770661253122413, -0.8643346460627238, -0.9767649907909008, -0.8307717384719447, -0.8470834948865624, -0.9327191260887775, -14, -0.8480603980734929, -0.8719879246849204, -14, -0.9050759519464299, -0.8341188380414228, -0.8309981638406738, -14, -0.8298287369661544, -0.8529009617139138, -0.8281883689121128] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1689  total reward: -4915.93906198428
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7224856691942907, -2.1906065165516138, -1.4472078216301167, -1.2874186539210188, -1.1483118756220116, -1.1213004213743738, -1.1768084395348768, -1.1070142646994614, -1.150347780994402, -1.722728689626857, -14, -1.1243869298596305, -1.1314078267685765, -14, -1.2359429340288146, -1.1156671738469606, -1.187967489482347, -14, -1.1136974741957906, -1.111678061453033, -1.1138908935088068] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1690  total reward: -4917.807917398026
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.373463664774927, -1.2666083569025142, -1.109840939340821, -0.84944957090783, -0.8092549968066143, -0.8271239943995007, -0.9367466486471414, -0.7548294633249177, -0.7603424707376422, -0.8020254354666259, -14, -0.7749015682414094, -0.7893507941003735, -14, -14, -0.7628464816246922, -0.771128652963583, -14, -0.7634997152652161, -0.7759828836351923, -0.7618411490459311] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1691  total reward: -4919.172116626807
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.02491170505383, -1.0605059243578656, -0.8519459932349466, -0.7099089703132003, -0.6453373080372964, -0.6281941962815574, -0.7214827183805573, -0.6149677196930321, -0.6232633890431687, -0.6774292568290972, -14, -0.6216201549273888, -0.6402626428795912, -14, -0.674478860924855, -0.6137445783889887, -0.6072243680978004, -14, -0.6112685776472148, -0.6286739175522167, -0.6093697654569793] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1692  total reward: -4920.463437943877
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1611140640402475, -1.2668116676709853, -0.9313102845498799, -0.7732632091537555, -0.7179886679677182, -0.7079224584951194, -0.7912812243745765, -0.703718739600688, -0.6897903826269394, -14, -14, -0.7078751418507603, -0.7394665307087774, -14, -0.7458747522512561, -0.692842244380287, -0.6851690158647484, -14, -0.6884339946628335, -14, -0.6840969489717693] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1693  total reward: -4921.891780838624
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3016631770091687, -1.3835199000460052, -1.0034236205218119, -0.8306091918417241, -0.7823765624735542, -0.7724210923830875, -0.8626784456862896, -0.7565077052809547, -0.7539414126627472, -14, -14, -0.767527232562005, -0.8039864559943255, -14, -0.8064135581846112, -0.7534657924289545, -0.7458560236631199, -14, -0.7502548080501663, -14, -0.744245945775582] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1694  total reward: -4923.216900906988
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9389584282003821, -1.0421961320617055, -0.8171785036423298, -0.6511835621483392, -0.6061119014197055, -0.6142455542286209, -0.6557631509897762, -0.5974954526493984, -0.5861019502518271, -14, -14, -0.6033208282353224, -0.6402126127594865, -14, -0.6349243777791149, -0.5871556703985683, -0.5777919640637543, -14, -0.5872546528065896, -14, -0.5808741225886397] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1695  total reward: -4924.548237548561
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3594248243670324, -1.1875918237181187, -1.1680848753847817, -0.8256020610817056, -0.7989076959489065, -0.8692413120844014, -0.9223418991103424, -0.7723822498145916, -0.7597381532107599, -0.7754817583476918, -14, -0.7671900425554251, -0.7899113341258954, -14, -0.8047692647483362, -0.7565462497753577, -0.745276458662219, -14, -0.7559026780883156, -0.7829188059990176, -0.7535446775087163] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1696  total reward: -4925.805694041105
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8627860848084767, -0.9344883107380629, -0.7186568816054345, -0.5651655360193856, -0.5353980205095814, -0.5468375248254648, -0.5763440996601785, -0.5305637117101907, -0.514407221593009, -14, -14, -0.5292235490226611, -0.5536352659115079, -14, -0.5555002697412985, -0.5175767677948852, -0.5100707276314457, -14, -0.5158377255128084, -14, -0.5121800338815603] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1697  total reward: -4926.731780414901
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7068390752168487, -0.6997837472645942, -0.58795433735485, -0.46882501979269214, -0.43941167102218937, -0.4400865954774818, -0.4880521877272485, -0.42524502984513324, -0.4236920612135285, -0.45856813365483035, -14, -0.4248828129565387, -0.4368058774624708, -14, -0.46493252396249435, -0.41892666139135143, -0.41720821667598457, -14, -0.416981139580673, -0.42972091756523767, -0.41601564616441944] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1698  total reward: -4927.591953667068
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7971405457550209, -0.816376389382547, -0.6376789672919122, -0.5530208616569039, -0.4788549855098968, -0.4496011924646059, -0.5690760868859034, -0.440297321398798, -0.4631073642847975, -0.4773087511249014, -14, -0.4574072296796455, -0.47538217514984, -14, -0.44029732139879807, -0.4418720783630699, -0.4394012258539955, -14, -0.44581317014699084, -0.47834376283458735, -0.44415760600302995] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1699  total reward: -4928.514087131591
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7736035741929789, -0.882395679211975, -0.6614410937523301, -0.5327813697864511, -0.500788457484517, -0.5087027482938863, -0.5245953016465267, -0.5035434524317592, -0.48478829244969623, -14, -14, -0.5004707899453545, -0.5265856726448654, -14, -0.5292388718782076, -0.4857202672695976, -0.47627463487081795, -14, -0.4867652640202177, -14, -0.48273223866798787] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1700  total reward: -4929.474264539947
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8151154813279863, -0.8572437457274426, -0.6645489424957838, -0.5604220415891288, -0.5113481698455034, -0.49666347156640694, -0.5648719018210885, -0.48735280454793256, -0.49537819157313717, -0.5463013372365453, -14, -0.49568413155578717, -0.5111155502172435, -14, -0.5362319378509472, -0.48757937326339684, -0.48698998509680785, -14, -0.48531936192041797, -0.496606821609119, -0.48390277348611305] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1701  total reward: -4930.7842277414675
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4643244572756413, -1.448023311809326, -1.192708480811116, -0.9403950585465477, -0.8771233909509603, -0.8759098291485717, -0.9836516578075547, -0.8293715288753933, -0.8407618713327342, -0.91977065443581, -14, -0.8429950401898482, -0.8652513994080359, -14, -0.887171946446558, -0.8320254010760367, -0.8258816436332583, -14, -0.8277771894695273, -0.8472639742739603, -0.8260604280337723] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1702  total reward: -4932.508371903328
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5295663310538747, -1.614964883810248, -1.2706487659644785, -1.000248293798797, -0.9430030588689685, -0.9573905038170841, -1.0422485273360471, -0.9240163974625871, -0.9051686601234151, -14, -14, -0.928228412591051, -0.9719177773785971, -14, -0.9768994913918928, -0.9099596933338703, -0.8997560187298774, -14, -0.9049384817084366, -14, -0.8982625182276527] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1703  total reward: -4934.3277351746965
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5080929707212736, -1.7059854686428717, -1.2863784630851816, -1.054849864032904, -0.9639061773280089, -0.956631110853063, -1.0553830721857218, -0.9403937762445316, -0.9294199148271933, -14, -14, -0.9537238456165495, -1.008105690550518, -14, -0.9929990632552756, -0.9316080780996185, -0.9175601212399929, -14, -0.9306363543488555, -14, -0.9211007531414273] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1704  total reward: -4936.284397499929
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7449821649913033, -1.7660815950018207, -1.500322187666737, -1.1882874029772552, -1.098478259518004, -1.0994101167426302, -1.2226077377354145, -1.041191048139417, -1.0665888569333397, -1.1646969566224736, -14, -1.0644533746955225, -1.1010821621383136, -14, -1.1479448939811137, -1.0460444611179618, -1.0430661269178554, -14, -1.043041355522151, -1.0762771825645163, -1.0391022039921238] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1705  total reward: -4938.323414328326
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7566919010050799, -1.7431619979591952, -1.3870804751138357, -1.1535064224410985, -1.063020382346185, -1.03282114277537, -1.2037217370867435, -1.0072030998132642, -1.020237820034769, -1.0995230483027265, -14, -1.0226807705525442, -1.0537348076137918, -14, -1.090740090501144, -1.0062786569750273, -0.9963868502581124, -14, -1.002469550733377, -1.036130909006094, -0.9999146244042686] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1706  total reward: -4940.331100406314
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6918055239791636, -1.8482519243008146, -1.4226363128376034, -1.1462495532680184, -1.0610772651078093, -1.060895083934418, -1.1725851050809843, -1.0285465512890162, -1.0259532878439368, -14, -14, -1.042546450401648, -1.090580483311953, -14, -1.102370301196563, -1.0239204017618322, -1.0149973748245937, -14, -1.019065744170299, -14, -1.0112992277302961] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1707  total reward: -4942.80760659391
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.8315643257933911, -1.5994534477790896, -1.4679559988471234, -1.4851352945736263, -1.4116218061046497, -1.4990580014959922, -1.4732230392056278, -14, -14, -1.5037841962041159, -1.5705115238842378, -14, -1.5638778669717461, -1.4253826579808848, -1.367210611302769, -14, -1.477324358983054, -14, -1.4652069598658177] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1708  total reward: -4944.652916248577
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4856682183373888, -0.481546001287621, -0.6046355871892634, -0.5462057400463487, -0.47598139731053746, -0.4810167463561463, -0.4808824450489856, -0.6092959038942973, -0.4778295507922692, -0.49358038969097806, -14, -0.5018910930984701, -0.5294564635416651, -14, -0.657671097400711, -0.4798373856596253, -0.4829483508587872, -14, -0.48134534558722236, -0.5064428705106073, -0.4780990433637489] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1709  total reward: -4946.200913659408
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5438784836344526, -1.6410478886396491, -1.392327180877345, -1.2140983461558426, -1.039689303388177, -1.0902937105712744, -1.1593887140797745, -1.0750744299629018, -1.0996802947290591, -1.6406726014550483, -14, -1.08197608174908, -1.0922931272266136, -14, -1.1858889209171797, -1.0829702777991403, -1.0987783508643534, -14, -1.0719278457730705, -1.066844301739201, -1.0720160135212715] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1710  total reward: -4948.097350765332
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.27167878775996, -1.6572456823807866, -1.076498192399588, -0.9736501545424985, -0.8756727843743618, -0.8597879317256685, -0.8833358838661846, -0.8654742621001456, -0.8785879663852224, -1.3506650966732876, -14, -0.865108946527052, -0.8685248823533225, -14, -0.9778762750604174, -0.8540260416031459, -0.9476179654091931, -14, -0.8563702142230141, -0.857030411584201, -0.8567478025351848] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1711  total reward: -4949.646251802811
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.174526472600571, -1.2043241740415485, -0.9594432312914923, -0.8035802542611898, -0.7354911003549042, -0.7152592459414812, -0.8030939263509667, -0.6981323576466306, -0.7091355625761193, -0.75473836254697, -0.7296794217663034, -0.7126506907609941, -0.7280647678720192, -14, -0.7663764744311878, -0.6893959054387894, -0.7015274024171116, -0.710690291224795, -0.6963408133810245, -0.7117900222815978, -0.6948749958761276] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1712  total reward: -4951.305904078254
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6946023159931376, -1.7482252358362624, -1.3699737251971238, -1.131501120522077, -1.0308791925121459, -1.002746669959402, -1.1556872393376605, -0.9691820405025996, -0.990095344920858, -1.1120082764149957, -14, -0.9902975361856242, -1.017070692640873, -14, -1.039774294765374, -0.9777053889684192, -0.9761870436711879, -14, -0.9724646500132119, -0.9964580251399433, -0.970256370004335] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1713  total reward: -4953.21200580153
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.604924220352389, -1.5478191216579729, -1.3514363684274215, -1.0726233353947034, -0.9946862747339192, -0.9912645821483199, -1.1518380740361958, -0.9157670016868736, -0.9338844411153353, -0.9843893003822861, -14, -0.9558964835079454, -0.9730255229222997, -14, -14, -0.9393220121354496, -0.9595282713058638, -14, -0.9380772013634605, -0.9493509418948964, -0.9369196827734687] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1714  total reward: -4955.295242289627
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7936924751863053, -2.2367325973409753, -1.5249683606324433, -1.318932529652392, -1.2015627427585573, -1.1867818243131179, -1.2215887104140024, -1.1712459708025837, -1.200536805292033, -1.7760645546157574, -14, -1.1773100453127803, -1.1860365811707578, -14, -1.317497798753305, -1.168684664756974, -1.2702949011113718, -14, -1.1677414033286224, -1.1652816727527902, -1.1674694864100137] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1715  total reward: -4957.144913531869
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.234798298637261, -1.1699232322145328, -0.9480827031512036, -0.7883720094250651, -0.7303266898933894, -0.7080849165131036, -0.9094767091143287, -0.6810188969847125, -0.715267412713064, -14, -14, -0.6939754434524478, -0.699705690662663, -14, -0.7689598010221895, -0.6874930980140544, -14, -14, -0.6844195277784688, -0.669311584806526, -0.6843895694896617] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1716  total reward: -4958.510223023072
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2537876256480738, -1.214026394129692, -0.9776751911938579, -0.7816568732371425, -0.7385844323373981, -0.7348856873186795, -0.8269722096917247, -0.6990802467908094, -0.7097718829752525, -0.7761674282405129, -14, -0.7109520531987906, -0.7289943001402341, -14, -0.7537896670191213, -0.7007533177244437, -0.6966547325491244, -14, -0.697072270518587, -0.7178828349287499, -0.6959979063964491] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1717  total reward: -4959.952673517554
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.316717464792283, -1.2711369352961244, -1.0700965780735454, -0.8459206680982911, -0.7924846797344807, -0.7919891930770752, -0.8958694437086332, -0.7437615946478078, -0.7663324410100939, -0.8139515963944062, -14, -0.7648392372945151, -0.7915181675459305, -14, -0.812179738453976, -0.7497405134290065, -0.7424676783486883, -14, -0.7491548949896308, -0.7798501945371024, -0.7464525880854217] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1718  total reward: -4961.330972616257
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.042564641881052, -1.1806652644527593, -0.883542976714581, -0.7228091383133959, -0.6645003760914312, -0.6615999703414203, -0.7211843138353693, -0.6487724290892473, -0.6424013316365433, -14, -14, -0.6608017556564265, -0.6955243196261965, -14, -0.6879097766005459, -0.6428430202087877, -0.6330458622135537, -14, -0.6408622695753389, -14, -0.6358314203544884] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1719  total reward: -4962.434107928823
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.783803232077795, -0.8445129487364902, -0.6267044276462379, -0.5476081979088434, -0.4958805336563399, -0.4765211195410572, -0.5442684286640131, -0.4700503881473035, -0.4844116124173254, -0.5503456684561526, -14, -0.4813839182055867, -0.4943875794480409, -14, -0.5248861152945455, -0.47377997863246296, -0.4730449360494148, -14, -0.4709401852221304, -0.4810679600670308, -0.4700894503523239] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1720  total reward: -4963.331392329659
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7507853405750683, -0.7157842775199329, -0.6073343916489059, -0.4768002902173933, -0.45240849247979387, -0.4569116109768992, -0.5145983678449588, -0.42165770832602384, -0.4267291417044904, -0.4544601121638039, -14, -0.4363446890101688, -0.4441001633821643, -14, -14, -0.42751122254519835, -0.43762731365424873, -14, -0.42789039698695785, -0.43221041371252994, -0.42723401268909234] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1721  total reward: -4964.27257471327
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9035459724590841, -0.8432281332515074, -0.817804882086062, -0.5759567991871463, -0.5498318862975458, -0.5967548765464465, -0.6197525482367662, -0.5310628025651689, -0.5243279551874639, -0.5534399498717101, -14, -0.5285099801734388, -0.5410775736626249, -14, -0.5567968764817434, -0.5227833932574462, -0.5169617481133519, -14, -0.5204647051481253, -0.5330685246411111, -0.5195246752838332] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1722  total reward: -4965.308331794557
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.716836342055142, -1.029321194373631, -0.6565097192749222, -0.5665891014530815, -0.5178547208787749, -0.5284040839104543, -0.498675735062628, -0.5412013521547375, -0.5198562164949817, -14, -14, -0.5323869772857727, -0.5522898080410144, -14, -0.5618051235687676, -0.5030654671615258, -0.4858120313810369, -14, -0.5218511342486368, -14, -0.5187953331736675] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1723  total reward: -4966.2260414965385
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7525586607408598, -0.7436042552171318, -0.6160304430997139, -0.4991217688045443, -0.4592462094836249, -0.4511355899776257, -0.5218662353782415, -0.437160780622575, -0.43930801244542406, -0.4655013632428034, -14, -0.44135874456243096, -0.4550464044878108, -14, -0.4698462094450264, -0.43442218293574825, -0.42880153902690665, -14, -0.43314288222477687, -0.4464881075583726, -0.4318976706011154] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1724  total reward: -4967.269318715973
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0333410872141522, -1.1306764507457214, -0.8517688183719927, -0.6836261653268932, -0.642643146446594, -0.6476899510632766, -0.6942439414807482, -0.6363457811269049, -0.6168077446040633, -14, -14, -0.6332673122559404, -0.6629516248600219, -14, -0.6642989181430494, -0.6208218454051848, -0.6111235573794229, -14, -0.6194112564642308, -14, -0.6144756804076676] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1725  total reward: -4968.628212296646
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3047483575374972, -1.295707146996408, -1.0457135700850135, -0.8480396464513572, -0.7920960138046012, -0.7828685515632274, -0.8836820177008371, -0.7586922422650659, -0.7608216273980997, -0.8422032675762865, -14, -0.7628065163642516, -0.785191084599914, -14, -0.8207093514549046, -0.7537753286875358, -0.7521744431607343, -14, -0.7500963344127725, -0.7655553588579761, -0.7477700232931503] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1726  total reward: -4970.163150565018
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3400573501201865, -1.3865331399512817, -1.079330440476101, -0.9007803296952953, -0.8315563454920822, -0.812359805130861, -0.916438984489095, -0.7830186458829196, -0.8129222722052832, -0.907080180322437, -14, -0.8061531423412975, -0.8318650653836969, -14, -0.8728434612763519, -0.7925378020529851, -0.7932037148157747, -14, -0.7896779035858765, -0.8149848791142226, -0.7871682450793521] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1727  total reward: -4971.842880830662
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5113975830329596, -1.6422572971936693, -1.2207301933936432, -1.0628389718799254, -0.9493224840848691, -0.9088613080440725, -1.0667086112115862, -0.9012561056155013, -0.9144633110865715, -1.024988055035088, -14, -0.9181861230929811, -0.9335917989757678, -14, -14, -0.8962631253873591, -0.9245245269832344, -14, -0.8982840415775634, -0.9060766485823113, -0.8967116197598244] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1728  total reward: -4973.656747292491
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.588568311342766, -1.6219202182725996, -1.2311349230393407, -1.0794028503631492, -0.9763129876139386, -0.9291976959485678, -1.1098090181582803, -0.9190150164243145, -0.9204986444533964, -0.9773177120802709, -0.9499118957904689, -0.9419113054168593, -0.9590812691210207, -14, -14, -0.916912646955891, -0.9397897771772731, -0.931955031591366, -0.920491687923958, -0.9286684936292303, -0.9176033364426751] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1729  total reward: -4975.649532006525
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9364708132309982, -1.8710742122818202, -1.5556275519290408, -1.241995047567261, -1.1482500202864978, -1.1316985371619699, -1.3406995513045266, -1.077528905827695, -1.0806858871286091, -1.149629290536635, -14, -1.0987942025985311, -1.1222254789351707, -14, -14, -1.0771789109785461, -1.0883479871030297, -14, -1.078673682152566, -1.10148010984074, -1.0758720670782689] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1730  total reward: -4977.752078779049
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8012926161627798, -1.8456038553101732, -1.4193056344668666, -1.199504417239112, -1.092040951511813, -1.0519926474842363, -1.248140308526382, -1.0251669879225476, -1.0320468490263248, -1.1378920120747076, -14, -1.047077437787134, -1.0649253292462733, -14, -14, -1.027519405271664, -1.052900918349024, -14, -1.0284555832840838, -1.0409219474098579, -1.0266747054452996] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1731  total reward: -4980.096942261653
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.717680972247121, -1.526489312051746, -1.3578150443395678, -1.3288766396395981, -1.3886647600520012, -1.3154301989309551, -1.3612346899538648, -2.0322378417812716, -14, -1.3298779972032961, -1.33646950393549, -14, -1.474199932938693, -1.3195265632250914, -1.400182427868253, -14, -1.3193745773550176, -1.3170096476744595, -1.3196964946815257] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1732  total reward: -4982.44672042795
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.834959117619066, -1.7204625579629624, -1.5005213506769195, -1.1566232891747663, -1.0973526518578807, -1.117418376018284, -1.2617566045285897, -1.019119834456944, -1.0313712014612135, -1.0967973886659526, -14, -1.0526289214363427, -1.0715771017938405, -14, -14, -1.0360397872646814, -1.0559674081188708, -14, -1.036280168943775, -1.047816299738065, -1.0343479673660698] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1733  total reward: -4984.2465065994875
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3767110193806882, -1.3026730970465312, -1.1378172783163225, -0.8780480695769635, -0.828417459488898, -0.8411836368211224, -0.939871758709622, -0.7976197778366, -0.790532470231307, -0.8334724366787314, -14, -0.7967331967310995, -0.8197286611630631, -14, -0.8484771846863697, -0.7863721286130388, -0.7754151272737577, -14, -0.7826597676899313, -0.8027264852971799, -0.780666337080714] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1734  total reward: -4985.757822647596
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2495202869508355, -1.2641654170045602, -1.1042782140705352, -0.8247037806556538, -0.7757807543057076, -0.809024254617663, -0.8890225099516066, -0.7580732768393381, -0.740718375949085, -14, -14, -0.7581341051272142, -0.7878841024649824, -14, -0.798569103472682, -0.7466948099676068, -0.7420741313138991, -14, -0.7400204842935515, -14, -0.7359009208354369] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1735  total reward: -4987.252371889473
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2639706774375619, -1.4393899534038936, -1.0442213357213326, -0.8597724087112781, -0.7928160259462229, -0.7868457282692066, -0.8541960091447743, -0.7719404053107126, -0.7648569046311064, -14, -14, -0.7852870329862761, -0.8270507865914694, -14, -0.810054191968053, -0.7655909156459412, -0.7528854670909914, -14, -0.7655392895520714, -14, -0.7586483210405388] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1736  total reward: -4988.97919753556
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.647677342572837, -1.7314113167235299, -1.3554790996888673, -1.1439131582890318, -1.032262619856201, -0.9980169499028008, -1.1539669846126668, -0.9739987940033813, -0.9979952254403218, -1.1105227307056886, -14, -0.9976966786022047, -1.0320156749258396, -14, -1.063994500904688, -0.981533225472761, -0.9789812544884848, -14, -0.9777221531565253, -0.9995466624012463, -0.9739401789960613] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1737  total reward: -4990.882569116906
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5934480496780188, -1.6611876570008384, -1.288413029264012, -1.0870078176200497, -0.9858063116408928, -0.9527519404817011, -1.1024204180143624, -0.9328635742541085, -0.9490533721568146, -1.0535655582597012, -14, -0.9512510978677361, -0.979756767226341, -14, -1.0107843619119903, -0.9371132175743959, -0.9319832261516634, -14, -0.9318933378409259, -0.9500728120605152, -0.9294314023501844] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1738  total reward: -4992.528409310071
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2325770368153528, -1.2676649763137844, -0.9948853184497665, -0.8321562330568325, -0.7598186342244345, -0.7374085122183894, -0.8504594784558286, -0.7183102161225227, -0.7326617071690043, -0.8143212572615709, -14, -0.7334792515372429, -0.7549520035002201, -14, -0.781644140652606, -0.7222573816095387, -0.7170031725987044, -14, -0.7180736777311219, -0.7326785014786393, -0.7164087908146383] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1739  total reward: -4993.979841013372
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2390770071627013, -1.3457599247963004, -1.004231836187957, -0.8648074622280332, -0.7770057433260995, -0.7475410187806161, -0.8562914332636861, -0.7247113135885127, -0.7618742429813107, -0.8728262675199315, -14, -0.7521022235265139, -0.7754262376084748, -14, -0.8016105150012003, -0.7400051002841102, -0.7428331638436576, -14, -0.7373776194861336, -0.7591090390105582, -0.7350229124862543] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1740  total reward: -4995.5495227175215
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4804706320275276, -1.414340040447139, -1.2222094084243271, -0.9483298625431629, -0.8955815396401341, -0.9083104855471215, -1.022755660211867, -0.8318172886164152, -0.8427743754768094, -0.9001830356755477, -14, -0.858235124953068, -0.8728668404239046, -14, -14, -0.8461062850075074, -0.8613287126116522, -14, -0.8466240344186874, -0.8536657833642745, -0.8449703905616921] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1741  total reward: -4997.821231233607
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
    depth 1: 5 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.85890952346803, -1.4548258535682785, -1.5133415286022756, -1.6290854012990477, -14, -1.4958504410663824, -1.4432393359947229, -1.440015850309076, -14, -1.4598999766299297, -1.4972020257560699, -14, -1.5098897993194742, -1.4442282702104658, -1.422144635378586, -14, -1.4437152250547283, -1.4864834335896921, -1.4398912274691875] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1742  total reward: -4999.890778098765
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1232482542086715, -1.1556107407158995, -0.909228899002216, -0.722058526773784, -0.6818311629787925, -0.686861708064756, -0.7676093708336783, -0.6615615448888007, -0.6536963554746477, -14, -14, -0.670357231955545, -0.7047799541049555, -14, -0.7009122366567296, -0.6562378364963631, -0.6501134170381324, -14, -0.6528245893957617, -14, -0.6474022297788898] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1743  total reward: -5000.996894281639
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7724774491881434, -0.8457504993347411, -0.6401954823487457, -0.5166947617485435, -0.48085731380835245, -0.4811279829609892, -0.5267520214322554, -0.47192757562869303, -0.4612098085829631, -14, -14, -0.475560406326383, -0.4982065301027318, -14, -0.49431629531440324, -0.46401895612361166, -0.4576440983301079, -14, -0.46186720028281064, -14, -0.458713953094782] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1744  total reward: -5001.849181069665
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6601617324371908, -0.7087605735867694, -0.5531277332377347, -0.46564147284045543, -0.41763132380840146, -0.4044809490875074, -0.4636550750707753, -0.39620093232330805, -0.4034303491613338, -0.4509448701891685, -14, -0.4032622255027438, -0.41315315081408194, -14, -0.4314026553690667, -0.3978322198065296, -0.3945619456543731, -14, -0.39518534526358223, -0.4023167439513255, -0.39464268969610683] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1745  total reward: -5002.617578359877
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6208681978020313, -0.6873906316488214, -0.5040806592812536, -0.4154972522687041, -0.39012024190086664, -0.3890647410377351, -0.4182349242708086, -0.3880358840904545, -0.3755525406595551, -14, -14, -0.38726719388890524, -0.40861858242945387, -14, -0.40728122397264793, -0.37737784906971694, -0.37056984628689377, -14, -0.3774080036744666, -14, -0.37383534455806194] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1746  total reward: -5003.326663967327
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.591812791551266, -0.6094874444180617, -0.46963446511243767, -0.3892182899778412, -0.3587546738678171, -0.3499292750889743, -0.39786454775810726, -0.3381184430663716, -0.3463678460434476, -0.3893009095567571, -14, -0.3464849571277021, -0.35557422081634454, -14, -0.36673466613494, -0.34110357426616, -0.34082822761642423, -14, -0.3390781005731688, -0.3463431729990148, -0.3385157611619504] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1747  total reward: -5004.112307248115
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.776280285441389, -0.7611012825780702, -0.636287873126252, -0.5045396563977353, -0.47379297716980806, -0.4747069322754854, -0.5365375447609579, -0.44551911532304633, -0.45002287109934247, -0.48721839057464617, -14, -0.4581959690004784, -0.4674118930841024, -14, -14, -0.4477661947265518, -0.4619764308682772, -14, -0.448552608126677, -0.45399337003065066, -0.4475248377219784] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1748  total reward: -5005.035018376985
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7961974663113108, -0.8516033480499084, -0.6452781882046931, -0.5479424345263483, -0.50249032558557, -0.48882055107071526, -0.5473189998800816, -0.4753511264287982, -0.4932670676106966, -0.5639778948997614, -14, -0.4904278545873119, -0.5077838913289381, -14, -0.5340699957542789, -0.4807371034018869, -0.48416309579113326, -14, -0.4791301207500872, -0.4858544706216074, -0.47719201354706076] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1749  total reward: -5006.279031031829
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3072931241316874, -1.3391768135901754, -1.1093285815074465, -0.8755672275184134, -0.8123204034141054, -0.8148350162831655, -0.9072020067344818, -0.7663581425110035, -0.7740254615004043, -0.8517027425636999, -14, -0.7841039767541437, -0.7971582811562563, -14, -14, -0.76866501148582, -0.8011971003288346, -14, -0.7700830365851149, -0.7804774490541858, -0.7686615284144076] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1750  total reward: -5007.965545488234
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.627424225715105, -1.6128161276995134, -1.294970744235152, -1.054413295042835, -0.9777158387506749, -0.9597011818122704, -1.1016193710380524, -0.9252579967459202, -0.9379415886028835, -1.0249728653059336, -14, -0.9396654717001459, -0.9664973075985218, -14, -0.9970065412315601, -0.926761415615874, -0.9179020798249821, -14, -0.9224437069022714, -0.9445334965529077, -0.9201563138948867] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1751  total reward: -5009.849708608739
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5936404073881965, -1.7242203692394171, -1.3449145609908149, -1.0784829775040676, -1.01072595611288, -1.0196828427832567, -1.1042917598753768, -1.0126197220941553, -0.969883143675805, -14, -14, -0.9960899223339162, -1.0407928297749103, -14, -1.064324120050545, -0.9784116604539084, -0.9651193591583614, -14, -0.9732981147397344, -14, -0.9662610406799399] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1752  total reward: -5012.496504116751
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.5470376655632467, -2.0121928656585575, -1.8114216519038406, -1.7666382705890098, -2.1493014558240953, -1.6660086113526635, -1.7364496697225302, -1.8085647404422482, -14, -1.7150699275810906, -1.77021676465363, -14, -1.6660086113526635, -1.6786831476469009, -1.6678023596605704, -14, -1.6878243221657947, -1.7748943846453076, -1.681676148853611] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1753  total reward: -5015.084150853172
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6260957355146686, -1.5967187065493427, -1.264918346996556, -1.0465348983626759, -0.9778839137366953, -0.9563566468543437, -1.1142453366323735, -0.9195693260924308, -0.928287406066018, -0.9973963372000002, -14, -0.9415684362031904, -0.9615732529493523, -14, -14, -0.9218317388988903, -0.9456728608912146, -14, -0.9243312008825093, -0.9398703023728662, -0.921638125068715] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1754  total reward: -5016.961141310979
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6710392973910089, -1.616341859421096, -1.3837536730194193, -1.0800216060695913, -1.0147787542345883, -1.0239800362515015, -1.1416353683295353, -0.9647168501696699, -0.9761935317503956, -1.0396567312060676, -14, -0.980931299312853, -1.0164459404746875, -14, -1.043452051104298, -0.9635984376306416, -0.9600293441740754, -14, -0.9614866836777448, -0.9955891189542735, -0.957421131714276] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1755  total reward: -5018.5016225673235
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6048510087607668, -0.5971063536059625, -0.7589994824582272, -0.6854291712401084, -0.5742073211555347, -0.585664805874312, -0.5818445750193183, -0.7294016782785766, -0.5837300171495106, -0.5851089999693675, -14, -0.6073605014213252, -0.6336598144348878, -14, -0.8076767867549574, -0.5857643322585067, -0.5980840414608065, -14, -0.5859427600491159, -0.609268487269639, -0.5830601246304485] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1756  total reward: -5019.96918135537
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3694124641495902, -1.286258470172757, -1.2524184967096166, -1.011397841554936, -0.8426837721587878, -0.933861046292062, -1.0123723135252316, -0.9040600102243841, -0.9068060803372677, -0.986273323988889, -14, -0.9148934807933566, -0.946450927474805, -14, -0.9594981405735028, -0.9000179259748308, -0.8856469764810101, -14, -0.8961090482287554, -0.9293897646345401, -0.893351466890899] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1757  total reward: -5021.552377583666
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2516403297540801, -1.3182318523775989, -1.034420821454154, -0.856428783460845, -0.7825691092929756, -0.7654807774209677, -0.8631087600132956, -0.7460004286923562, -0.7555789867906041, -0.8486511481373339, -14, -0.7581272188426074, -0.7808348168326337, -14, -0.8112110566610015, -0.7466408435899486, -0.7511305853842766, -14, -0.7426096703681517, -0.7558221659324124, -0.7405124561371141] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1758  total reward: -5023.11632728605
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.443823652340613, -1.4203259780629833, -1.1946823768421864, -0.9350394350069514, -0.8734703830679493, -0.8774098208202374, -0.9795800165302254, -0.826648734576883, -0.8402228828564291, -0.9133735711950596, -14, -0.8400167836733158, -0.8612771416324403, -14, -0.8922945123305902, -0.8287711246614771, -0.8209965174288044, -14, -0.8248344268233732, -0.8505212699420024, -0.823437246247372] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1759  total reward: -5024.808136702934
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8219889408448675, -1.5002301316393551, -1.0002593549789576, -0.8759528886422736, -0.9129448738612992, -0.9036904040244264, -1.012702540550246, -0.915684485172337, -0.8728681799475991, -14, -14, -0.9036879680432881, -0.9516569127696537, -14, -0.9564711544646008, -0.8823959706605001, -0.8711473161633039, -14, -0.878149188632472, -14, -0.8708128994547958] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1760  total reward: -5026.532309750593
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4116141022573987, -1.5565581215631439, -1.2026422130333212, -0.9703256387073966, -0.8945356369025372, -0.8942207815524573, -0.9867242597160024, -0.8728457325481489, -0.8618452556360775, -14, -14, -0.8856407943251108, -0.9250127269476307, -14, -0.926303397047836, -0.8640422485921047, -0.8537778212369798, -14, -0.8582060743804762, -14, -0.8533601482050326] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1761  total reward: -5028.470214545302
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8590927430148045, -1.9262912476935596, -1.5863787029983463, -1.223577025733335, -1.1435962538159856, -1.1662945641301703, -1.3000046538447891, -1.112386030889044, -1.0911011192963977, -14, -14, -1.1183625161554722, -1.1755477161174015, -14, -1.1655345504066332, -1.099753465494293, -1.0902892570015605, -14, -1.094710021039109, -14, -1.0845446465031312] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1762  total reward: -5030.30978878614
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2569250164250625, -1.3224901687130484, -1.0833717582584594, -0.8299610524046499, -0.7898241626615536, -0.8209003088658735, -0.8617488272041661, -0.7858339474741172, -0.7588898022681971, -14, -14, -0.779614109101166, -0.8168614151829523, -14, -0.8282958138658642, -0.7640680033630167, -0.7551144948099, -14, -0.7609611826527827, -14, -0.7550295943358658] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1763  total reward: -5031.920595516622
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.456616086742757, -1.5027857495963362, -1.2830202152191157, -0.9424781017408665, -0.8983221261990115, -0.9546642927335406, -0.9939795817871341, -0.8846741104953117, -0.8577051557709477, -14, -14, -0.8809001083560863, -0.919999537028265, -14, -0.9148925223538531, -0.8663309580996549, -0.8559643162094184, -14, -0.8621802131271382, -14, -0.8557771361451689] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1764  total reward: -5033.571223917454
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3848703854773448, -1.470837795807529, -1.088503860716235, -0.9015773618695522, -0.8380014504358464, -0.8231401241788224, -0.9428581733817405, -0.806930078360536, -0.8036880434531246, -14, -14, -0.8234153522341238, -0.8683704296221774, -14, -0.8535182486506289, -0.8054932139782063, -0.7970202905246146, -14, -0.802297934204071, -14, -0.794851264687077] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1765  total reward: -5035.031115235539
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0723737823410893, -1.216859603718809, -0.9139890874899758, -0.7523431165875687, -0.6934790772527704, -0.6908982323614389, -0.7481982643084211, -0.688344528682412, -0.670181176569647, -14, -14, -0.6892636929062516, -0.7277547334946369, -14, -0.7312628699458651, -0.6722771121700414, -0.6622424038767823, -14, -0.6714780962067352, -14, -0.6650400533976445] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1766  total reward: -5036.397223990738
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2245040349677307, -1.1732278598158024, -1.0765648000445598, -0.7900005060233095, -0.745811029246673, -0.7821348227613012, -0.8389097666044607, -0.7107947988307086, -0.7144862335175304, -0.7617604616098471, -14, -0.7187369708290616, -0.737319340035464, -14, -0.7567307729175398, -0.7082466235134192, -0.7017911190179829, -14, -0.7050504425294197, -0.7265090534428583, -0.7038663513218772] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1767  total reward: -5037.598060217921
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8230057572932393, -0.930107814764819, -0.673344866984952, -0.5584672522468624, -0.5202785434324749, -0.5171258947244436, -0.5555316361533225, -0.5158624185643241, -0.5014758231134875, -14, -14, -0.5182302466631475, -0.5481024114436452, -14, -0.5407113990761421, -0.503448156413704, -0.49355308475072823, -14, -0.5039394336807652, -14, -0.4990451081645525] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1768  total reward: -5038.50982805656
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7128827861763373, -0.7486717813828552, -0.5824883945529004, -0.4825061553737566, -0.4421198652397177, -0.4322817626295755, -0.4872632501910552, -0.41800028807650985, -0.42846178673297547, -0.4874620908360009, -14, -0.4285556486913117, -0.44082073395447524, -14, -0.4563503751182831, -0.4215153329375541, -0.4255952000564301, -14, -0.41915632822024895, -0.4288143034291886, -0.41821475388830265] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1769  total reward: -5039.281340500209
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6160831101570481, -0.6209787659080557, -0.49375990283947574, -0.4020182791561609, -0.37438355714175364, -0.36918079192571157, -0.42097350037746206, -0.351566521882409, -0.35483139049462814, -0.3905440479815687, -14, -0.36105703369460684, -0.3670393222251455, -14, -14, -0.35333711724588457, -0.3667642763967089, -14, -0.35405563477575347, -0.3573101894591174, -0.3535121555727956] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1770  total reward: -5039.961598123986
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5579493620770747, -0.5652216964684819, -0.46948146729517676, -0.3749150405280041, -0.3475289300290447, -0.34638675536431923, -0.38581513003034096, -0.3318319950048981, -0.3358069361857208, -0.3664084324047899, -14, -0.3361974667762655, -0.3467884726541732, -14, -0.3630773322565674, -0.3309736512708408, -0.32952458014765756, -14, -0.3297588209922304, -0.3376011928758481, -0.32869110189475914] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1771  total reward: -5040.67154217475
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6569119144345564, -0.6749545884843741, -0.5349484896133827, -0.4422462308187416, -0.40435793098952744, -0.39429264929477487, -0.4521394612591952, -0.37886343314030874, -0.39207639740267153, -0.42713657230511487, -14, -0.39018926205965765, -0.40244009166504763, -14, -0.41462548749119843, -0.3838670154153836, -0.3800679562022749, -14, -0.38239064291893005, -0.39393509765362533, -0.3812529488699667] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1772  total reward: -5041.586194278387
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9404293484425053, -0.9338506573156656, -0.7695948127373802, -0.6107488051088966, -0.5685859361571823, -0.566387226137974, -0.6460018076671625, -0.5354873863200399, -0.5397258254494012, -0.5846856387159569, -14, -0.5455868699675375, -0.555278108318421, -14, -14, -0.5362238408556282, -0.5458285355322545, -14, -0.5370075465252766, -0.5442024546863063, -0.5357886704962418] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1773  total reward: -5042.813560528342
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.185988440136532, -1.2099838689437634, -0.9593255898593038, -0.7835678821493047, -0.7306025486627304, -0.7218455615887981, -0.8036213335917003, -0.6962407498639103, -0.7086323662295815, -0.7879873503023921, -14, -0.7085338113302105, -0.7293307544269755, -14, -0.7670788702399873, -0.6970209967329861, -0.6974383435555682, -14, -0.6936193755290136, -0.7083756261185369, -0.6918788636353981] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1774  total reward: -5044.2517501580205
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2176375381464362, -1.2588286130938862, -1.086791079869218, -0.8683798309680344, -0.788802205110136, -0.784060862216376, -0.8812997447767787, -0.7480091323572577, -0.7673628737247251, -0.8238307563679236, -14, -0.7659219059020015, -0.7937503071895364, -14, -0.8299112416258322, -0.750792642762389, -0.7444075360014452, -14, -0.7492044731301177, -0.7745283043543935, -0.746310766043192] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1775  total reward: -5046.1755429328605
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-2.029353847362843, -1.9529442099740495, -1.8345427867495276, -1.293357093346769, -1.2427101613487332, -1.3601832589679264, -1.4326418092831121, -1.222087231320798, -1.1840830334947199, -14, -14, -1.2071654286282967, -1.2490586504150485, -14, -1.2774555912146444, -1.1963561582513336, -1.1909804093909169, -14, -1.1860238898906146, -14, -1.1793852388373236] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1776  total reward: -5048.143104936176
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.22287437294394, -1.4275145522226167, -1.0628791829570685, -0.9001402478391592, -0.8188441330692395, -0.8086797737876132, -0.8791934950972261, -0.823103013559184, -0.7949392145326372, -14, -14, -0.8185461536887636, -0.8599102004600662, -14, -0.8830613617990117, -0.7966706989513934, -0.7846912396154619, -14, -0.7940268214195412, -14, -0.7881767644788397] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1777  total reward: -5049.805600820012
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4540764709956677, -1.539082959197515, -1.242597465858179, -1.0256359441674545, -0.9277563065166802, -0.9078188758861834, -1.0288983889926835, -0.8866702890104942, -0.8966135254143596, -0.9992798780016641, -14, -0.8984582988271612, -0.9231017527191164, -14, -0.9701854315926847, -0.8847560240160565, -0.8812477834044598, -14, -0.8794723576724519, -0.8965511309964125, -0.8778046442203986] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1778  total reward: -5051.592200296424
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5484029919901756, -1.6230882484611295, -1.2906876732621306, -1.0705359030214896, -0.9645476001000716, -0.9368633314472993, -1.0814889390619402, -0.9076729449793121, -0.9298547072795087, -1.0189075068393956, -14, -0.9284945177231874, -0.9561480794058483, -14, -0.9831194442338618, -0.9150063004218525, -0.9089078448835604, -14, -0.9113446295506609, -0.9392070394692164, -0.9087948321925143] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1779  total reward: -5053.416404733344
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6051566436868934, -1.5503284252157663, -1.336726637513635, -1.0423785341133442, -0.9734963259582644, -0.9791875451052768, -1.1201568928196783, -0.9101555317367841, -0.9168147146885955, -0.9778319326934946, -14, -0.9341984868509846, -0.9510293257154012, -14, -14, -0.9178273767424413, -0.9307653740206516, -14, -0.9182090151236617, -0.9320130545561938, -0.9165314919404387] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1780  total reward: -5055.120352736517
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4231147316007606, -1.3844240084127653, -1.1092471140964502, -0.8914417817962672, -0.8418399428548091, -0.8359877050954202, -0.9405777282026423, -0.7952140187830398, -0.8117578368984328, -0.8835319903702159, -14, -0.8119077611673491, -0.8373101512456594, -14, -0.8640941938341805, -0.7988010689467456, -0.7939517919744836, -14, -0.796300646532329, -0.8164953735478907, -0.7937924714358096] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1781  total reward: -5056.573662892978
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1160716044191135, -1.179882323983489, -0.89498241611799, -0.7602795808986342, -0.6962538429325649, -0.6752284790205456, -0.76444545285417, -0.6655614980172315, -0.6740709763063206, -0.7634146752484765, -14, -0.6748045782852563, -0.692874846415857, -14, -0.7301475077144953, -0.6648604084411122, -0.6704577589997792, -14, -0.6607996405741022, -0.6751991797637031, -0.6595176850255869] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1782  total reward: -5057.909235619818
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1677761897508039, -1.1869583037745126, -0.9592408707526464, -0.7643460769303555, -0.7143647101694882, -0.713841127237938, -0.7856832375613655, -0.6762551704598715, -0.6933159412236394, -0.779263085785813, -14, -0.6886104022110169, -0.7057312699768601, -14, -0.7416747552892246, -0.6809014843148746, -0.6779411709421119, -14, -0.6775144563330405, -0.6921365735158599, -0.6760550418143422] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1783  total reward: -5059.266586187342
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1394044867149449, -1.1854484435628587, -0.9676376730237206, -0.7835439247508742, -0.7194237079398502, -0.7120247064990732, -0.7942356011160021, -0.6863382669174914, -0.6965530581258189, -0.7751962244146834, -14, -0.6983391719787619, -0.7194357181752019, -14, -0.7518652184359472, -0.6867102578054868, -0.6887081627483839, -14, -0.6830494143646748, -0.6982546530738175, -0.6812955257091488] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1784  total reward: -5061.119157764928
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4884174991845958, -1.3243998348734285, -1.2045998571487602, -1.1797427706945598, -1.2200007721313773, -1.1619571758352676, -1.2153593849613378, -1.828787740904112, -14, -1.1810550729247506, -1.1877003792699414, -14, -1.313974501874515, -1.1706817752458942, -1.251335931448655, -14, -1.1711336505098704, -1.1693034188178635, -1.1712760518766443] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1785  total reward: -5063.287677251834
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8050193011111617, -1.9151000693834628, -1.388860834346501, -1.2098314855121763, -1.0755560789538225, -1.0187365846699152, -1.244108233866128, -1.013368466071863, -1.25128656565415, -1.1266045832525893, -14, -1.0382740049815449, -1.0759314104344528, -14, -14, -1.0038856998180197, -1.0059187786897936, -14, -1.0169679951469925, -1.098109537086309, -1.0065623110711412] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1786  total reward: -5065.020805719181
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2481449443730797, -1.262220074314103, -1.0236138134504011, -0.843453056161555, -0.7736535622829467, -0.7559265551011303, -0.8709278097392176, -0.7291751403888392, -0.7315270645473761, -0.7732307636208458, -0.7530761789840836, -0.746222278620929, -0.758013710741255, -14, -14, -0.7288203692301574, -0.7446395342451737, -0.7397592491376629, -0.7311518043632227, -0.7379457515797507, -0.7292427675291908] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1787  total reward: -5066.420665894647
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1595278097192425, -1.1718408417147286, -0.9565680266602, -0.7720684643478638, -0.7117726135659801, -0.7024662263385757, -0.8081770636874418, -0.6696557233085886, -0.6752044055763416, -0.7330979940810315, -14, -0.6846830508408533, -0.697017949634115, -14, -14, -0.6712326479827578, -0.6863404157671618, -14, -0.6724195457956619, -0.6807176273468526, -0.6710398062353796] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1788  total reward: -5067.498681513571
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4184234982986137, -0.41475102889902393, -0.5179481811392856, -0.47008195210820586, -0.40456315644090995, -0.4103581175687512, -0.4088326485637453, -0.5263848738613002, -0.4076284301636833, -0.41194409940832577, -14, -0.42555404342594383, -0.4437383941179864, -14, -0.5635979058108477, -0.4105333235750604, -0.4179277093754539, -14, -0.410208627899924, -0.42416363376698046, -0.4083598956152726] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1789  total reward: -5068.6858671492855
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.193957439427162, -1.1365552917148392, -1.0918175855653913, -0.8902880477658077, -0.7389601556054098, -0.8136008364706049, -0.8849335145918736, -0.7835906869313537, -0.7997765181856574, -0.8962122443897155, -14, -0.8006001675451898, -0.8256628236072328, -14, -0.8443206972871569, -0.7873497481163553, -0.7740969426598997, -14, -0.7844693962039692, -0.8099278581421138, -0.7826224792742931] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1790  total reward: -5069.909502480878
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8508885502230403, -0.7975762637816158, -0.7475307285729822, -0.542143791698289, -0.5140380333314343, -0.5436124616974936, -0.5830089006302217, -0.4949576917180713, -0.4893256592153572, -0.5132176230813297, -14, -0.4935802415883264, -0.5069754681762354, -14, -0.5191749539157837, -0.4875996876980525, -0.4817393541167162, -14, -0.4859106071242948, -0.4982437421033031, -0.48467517598623927] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1791  total reward: -5070.800973819151
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7413588465372172, -0.7781222469065534, -0.5722648112364339, -0.500794133994591, -0.43958525196643067, -0.4141343950593178, -0.5444085743760975, -0.41120621711667676, -0.4333157009463004, -14, -14, -0.4213157297146261, -0.4388272237065492, -14, -0.41120621711667665, -0.41114330341682565, -0.41399488242003774, -14, -0.4125141747382239, -14, -0.4097319841571416] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1792  total reward: -5071.475920116944
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.4442595573515513, -0.48874002151976387, -0.3574462190985118, -0.2986343210958116, -0.2777072096434425, -0.2738987195805179, -0.3032688951752423, -0.2729760660350518, -0.2675647243472725, -14, -14, -0.2743384288396485, -0.28763710583907787, -14, -0.2900705196839881, -0.2682989090319423, -0.2649650426020109, -14, -0.26724575009002205, -14, -0.26521431363526426] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1793  total reward: -5072.12417046295
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6733520293587036, -0.6128885923688021, -0.6122438458365763, -0.4279177414445123, -0.406857873982772, -0.4417526312877358, -0.4677174902323735, -0.393684754060722, -0.385631541722514, -0.39889810108848806, -14, -0.3891690951279797, -0.39856158376710726, -14, -0.40635922585494105, -0.3852131123411008, -0.37953524955597123, -14, -0.3840849912568643, -0.3960046980318916, -0.38328530340508] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1794  total reward: -5072.72384650664
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.35007157238135383, -0.389831068227632, -0.31438146095193203, -0.24617943942429918, -0.22932691113103904, -0.23518194495992903, -0.24707184652518926, -0.2299899999254004, -0.2209063126213887, -14, -14, -0.22905394269174295, -0.24292606712805023, -14, -0.24095091191092785, -0.22237399696572036, -0.2184270456587006, -14, -0.2224126148953392, -14, -0.2201407941329449] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1795  total reward: -5073.165005087468
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.36331982766264626, -0.3936346470404232, -0.3071821314935085, -0.2587549677851149, -0.2344491635738343, -0.22863009543204643, -0.2560986714242514, -0.22171487896106232, -0.23058202912537357, -0.25722281211981723, -14, -0.22822653717671104, -0.23545590797032667, -14, -0.24990807062096215, -0.22429324393911437, -0.2239173279952751, -14, -0.22343092870635356, -0.22925977121401664, -0.22273153516963845] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1796  total reward: -5073.714567597182
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5751805589203478, -0.5849901608632061, -0.44381382965050753, -0.37597204311943344, -0.34762549189331804, -0.33628504413240334, -0.39213148312525237, -0.32617554976225877, -0.3293178325369089, -0.3659842986479301, -14, -0.33418677257748813, -0.33936414056674247, -14, -14, -0.32774768026258255, -0.3378996172440632, -14, -0.32832856078109046, -0.33067509203785866, -0.3278476307527099] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1797  total reward: -5074.497577940909
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8031979590191916, -0.8083704242809124, -0.6164678385645566, -0.5270502227795076, -0.4851899622531212, -0.4668196465460327, -0.5456141343636066, -0.45496787842856207, -0.47026775122064624, -0.5159004834128321, -14, -0.46649704094119276, -0.48157903118417766, -14, -0.5016011959106628, -0.45972146927333657, -0.45438620745141184, -14, -0.4584963818757682, -0.4717300273668787, -0.45683479396487714] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1798  total reward: -5075.482938336359
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8890521318566067, -0.9630388340769137, -0.7186702603860917, -0.5909927979707691, -0.555505638794794, -0.5534309073877856, -0.6042383173225089, -0.5489184450048794, -0.5348988983439817, -14, -14, -0.5510848893472624, -0.5826156151454263, -14, -0.5818104639846247, -0.5372631983559393, -0.5289536488741365, -14, -0.5361769692563825, -14, -0.5309741879996205] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1799  total reward: -5076.664431360403
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.164788710229821, -1.1112360706899667, -0.9418938244296853, -0.7295745555218914, -0.692010676557598, -0.7021124116333591, -0.7775699172265581, -0.6564494610228269, -0.6649046139777742, -0.7105917268059043, -14, -0.6667545128381469, -0.687255009917067, -14, -0.7068101287135969, -0.6567879851148506, -0.6510886850307238, -14, -0.654546441922912, -0.6742727291746188, -0.6525393751684601] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1800  total reward: -5077.918584336068
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9799538485469043, -1.1402619881465417, -0.8098132364519021, -0.6853682201647862, -0.6280864956809324, -0.6183740945547135, -0.671034096222482, -0.6164072204180064, -0.6095948817003526, -14, -14, -0.6244219189539076, -0.660719268387615, -14, -0.6558233178337771, -0.6088654077591266, -0.5981072245697958, -14, -0.6095474796658963, -14, -0.6030642906353767] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1801  total reward: -5079.248655904923
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2907648033815597, -1.2832150276690006, -1.056157525589004, -0.8453343593262141, -0.7787479978359472, -0.7685398998335778, -0.8817233465600364, -0.7317580645744204, -0.7472883704707016, -0.8097274350207758, -14, -0.7468890318682969, -0.7677580751578021, -14, -0.786655334920722, -0.7362824791498562, -0.7267601501738968, -14, -0.7337047234522743, -0.7526003977694388, -0.731964344285252] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1802  total reward: -5080.604438626225
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.015784058873994, -1.1254419647523373, -0.8812295579815684, -0.7141220530935077, -0.657836196785128, -0.6583729126905435, -0.7227273378029881, -0.647948714248379, -0.6361346760786816, -14, -14, -0.6503246124037835, -0.6841466819667634, -14, -0.6953554890493453, -0.6371621050293134, -0.6296561651576966, -14, -0.634675200342693, -14, -0.6290225711270349] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1803  total reward: -5081.7703317762
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8521050396231445, -0.9964935854781517, -0.7267860152885727, -0.6068891164235689, -0.5575496760037448, -0.5540588779239614, -0.5912299142677676, -0.5490531593377393, -0.54405212859603, -14, -14, -0.5586569500451797, -0.5892329234010227, -14, -0.5896721593677647, -0.541575914786322, -0.5321163154551263, -14, -0.5413477761991691, -14, -0.5368705788482393] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1804  total reward: -5082.83314584072
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9581825549876014, -0.9345029733354221, -0.7411144720237489, -0.5936773824055072, -0.5626353945135575, -0.5600095330642267, -0.6255959302427745, -0.5324340004915352, -0.5415030196299843, -0.5981988924299573, -14, -0.5423485812446356, -0.5560180067881094, -14, -0.575065319700969, -0.5345079471341195, -0.5317662192239441, -14, -0.5315348525570577, -0.5428594779291769, -0.5306977490650518] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1805  total reward: -5083.837353015203
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8187582883483154, -0.8494726456295343, -0.6443808866444273, -0.5371533078657968, -0.49987670664137634, -0.48913105303964577, -0.5464030045004438, -0.4747395977976976, -0.48526650882836225, -0.5539767467598667, -14, -0.4848655350907718, -0.49860839353210734, -14, -0.5220204758113837, -0.4771989683488338, -0.480610818610579, -14, -0.47466827519846383, -0.481756564816822, -0.47350942541803825] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1806  total reward: -5084.92020353117
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9292509353537317, -1.1845510619103556, -0.8079878155501646, -0.7099994252109834, -0.6283009121843814, -0.6153257149335477, -0.6470092727051152, -0.6100455313422218, -0.6259404118799867, -0.9183190926572522, -14, -0.6147503359177452, -0.618430284044958, -14, -0.6795916181616035, -0.6110393396123708, -0.6475883297831335, -14, -0.6092046656663425, -0.6078757869299808, -0.6093410905494662] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1807  total reward: -5086.029259824818
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8805312123949233, -0.8672713745791186, -0.7012487944530069, -0.572515922331286, -0.5319881934094917, -0.523032586158213, -0.6365580684912963, -0.49326970619751287, -0.5310651177082418, -14, -14, -0.5085228872740674, -0.5147765526964241, -14, -0.5620416278083578, -0.504158097306974, -14, -14, -0.5015806498200613, -0.4909675492386736, -0.5011805067180385] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1808  total reward: -5087.0649160363155
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9268883043933678, -0.9689823217542616, -0.748316384509759, -0.6267768348375412, -0.5755865650174833, -0.5608048221119973, -0.6343408301717619, -0.5456827508065908, -0.5590639440177552, -0.6281426927859771, -14, -0.557730336463234, -0.5752472314666666, -14, -0.6021697163628235, -0.5486817266701064, -0.5495929319241865, -14, -0.5464295645665898, -0.5573761580800655, -0.5446886622580962] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1809  total reward: -5088.215951281781
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1006183244891594, -1.0089126290382395, -0.8637589311251873, -0.6764655408936248, -0.6443696643968116, -0.6494528024210765, -0.7375944529058674, -0.61865700906193, -0.6148835270673964, -0.6431468658800907, -14, -0.618482512220197, -0.6358492808330904, -14, -0.6602976308591483, -0.6091285695894324, -0.6005857376516865, -14, -0.6076921621101775, -0.6298186971500933, -0.6063465832067185] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1810  total reward: -5089.357909040047
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9187306361578749, -0.9884515518464683, -0.758659406429674, -0.6130313202037991, -0.5691275518962218, -0.5672816521126758, -0.6341380655098552, -0.5534271999389966, -0.5469386470600375, -14, -14, -0.5594768173417853, -0.58585745008218, -14, -0.5877439814237873, -0.5485393622963307, -0.5432098828413392, -14, -0.5454005050385736, -14, -0.5413720206153267] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1811  total reward: -5090.395361538211
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8267112647150965, -0.9144339168651288, -0.6798053019441387, -0.5545889980316493, -0.5184572483815866, -0.5182637436239891, -0.5597623239589444, -0.5093164670962469, -0.5002970605553916, -14, -14, -0.5140355559959279, -0.5398099105915761, -14, -0.5393470667815958, -0.5014911495272778, -0.493570482366548, -14, -0.499951884358629, -14, -0.49608047754817575] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1812  total reward: -5091.436987684772
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9589679520376261, -0.9559084047289386, -0.797196248506286, -0.6244259157701041, -0.5812531852940171, -0.5830976892547322, -0.649699632718331, -0.5549713085684621, -0.5556381167560419, -0.6165567945710221, -14, -0.5579314310190218, -0.5709046084447734, -14, -0.5900818720483744, -0.5525476546095808, -0.5505124054633115, -14, -0.5489673186646338, -0.5598649621168232, -0.5480556641947893] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1813  total reward: -5092.480754186289
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8572699377830881, -0.8742297596863645, -0.706467235490593, -0.5755209566612219, -0.5262986072936007, -0.5158391946002762, -0.5909769823904559, -0.4973557835881199, -0.5055161139760946, -0.5572459097754408, -14, -0.5059010390920103, -0.5196076091398034, -14, -0.5352662055983449, -0.49940427421725064, -0.49809261307464026, -14, -0.49678277695077117, -0.5138258920368651, -0.4957108373219144] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1814  total reward: -5093.300646360081
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5627445946532534, -0.5596059771329768, -0.4615367649156225, -0.36848667299505083, -0.3434443193390832, -0.34186176394046025, -0.3836336483349834, -0.32670694077792334, -0.3307166990807618, -0.3647895604609461, -14, -0.3315342086162153, -0.3408875590475306, -14, -0.3544901268172553, -0.3266703408196298, -0.3247383695546773, -14, -0.32489956098112766, -0.33197593790901087, -0.32418133647035685] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1815  total reward: -5093.887241691265
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.45360612890513446, -0.45285732939229995, -0.3763521892611425, -0.30168443832543, -0.2784586094920882, -0.27565312248782314, -0.3133810200458991, -0.26355813333630645, -0.2679407204574829, -0.28969356824323617, -14, -0.2685637909835083, -0.2762840984377019, -14, -0.28535251620465163, -0.2642376938666066, -0.26208043429260314, -14, -0.2629486689432484, -0.2720676735488539, -0.26241399471352433] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1816  total reward: -5094.3574006757635
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3352156553076225, -0.3804420015168067, -0.28590948749514494, -0.23656325306925202, -0.21714536056607858, -0.21555538295926913, -0.23553564726232604, -0.21330025465471245, -0.21032047504235593, -14, -14, -0.21657208373483744, -0.22989701991853406, -14, -0.2274997522847613, -0.210379716120963, -0.20700149392019465, -14, -0.2102786483418665, -14, -0.2080785502060211] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1817  total reward: -5094.760008024768
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3348663374026734, -0.3316088140755684, -0.27866511574532987, -0.2211988369450334, -0.20686590354282205, -0.20720296312593012, -0.23047781142810328, -0.19894858162273357, -0.1991260574241738, -0.21554939234353837, -14, -0.20008947221977066, -0.20587995578569399, -14, -0.21613073170021202, -0.19710028850887784, -0.1961897042998934, -14, -0.1960609522395365, -0.20150853095547933, -0.19560585508357842] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1818  total reward: -5095.151736811245
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.346125002260597, -0.3398920778654638, -0.28090126443716534, -0.2192174472786416, -0.2075202201800833, -0.20998523443190947, -0.2297523696230706, -0.19838208257200626, -0.19950297792617958, -0.22188660649551817, -14, -0.19987175542076613, -0.20406603816932112, -14, -0.2138064300212052, -0.19760022919533926, -0.19656318484364618, -14, -0.196298528449417, -0.20001562893360564, -0.19612293139482706] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1819  total reward: -5095.5753996584235
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3955987783262618, -0.4148668644173466, -0.31492785910644144, -0.26274463723653557, -0.24093686530080924, -0.2343814963150664, -0.2658449486302878, -0.2260735186200095, -0.2337076312495892, -0.2672063477372576, -14, -0.23256876617934927, -0.23863401105555254, -14, -0.2463519161383264, -0.22920125915516418, -0.22933734562807215, -14, -0.22798423009142313, -0.2324689416851007, -0.22753991578305494] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1820  total reward: -5096.127920920699
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5885058390016498, -0.5591406998745208, -0.4797097686983755, -0.36807579744296065, -0.34719070877261243, -0.3524389912455445, -0.39983666626204245, -0.32654320900328004, -0.3280617740125691, -0.35285804796866926, -14, -0.33207657970928983, -0.33776663647964283, -14, -14, -0.32680015805934004, -0.330122103625384, -14, -0.3271024345532038, -0.33237575179184814, -0.32644774365447654] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1821  total reward: -5096.796859655205
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6022554397868608, -0.5976808339685602, -0.4852759219271571, -0.39238655110344, -0.3638176109381181, -0.3584918747580627, -0.41561408591663224, -0.34280771910594615, -0.3454151530484504, -0.3723381983488222, -14, -0.34979896602315413, -0.35696056665857756, -14, -14, -0.3425781405507573, -0.35047919424312535, -14, -0.34341698952266, -0.3494558635641803, -0.3424909908518704] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1822  total reward: -5097.632508192024
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0476303540910623, -0.7820676420110747, -0.5807656925363591, -0.5010386474594284, -0.5181738194891146, -0.5176104562579062, -0.603417337716394, -0.47519003579285174, -0.4940255689107576, -0.5079604144301347, -14, -0.5018782467304389, -0.5097607836813927, -14, -14, -0.4941820292480491, -0.5043718471785523, -14, -0.49357294486814374, -0.4958975261479628, -0.49315754596783157] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1823  total reward: -5098.586770621571
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8425279257506731, -0.8249835770014026, -0.6766081115352215, -0.5430761047756599, -0.5081266750744322, -0.5041957161342884, -0.5704928615620829, -0.4875031040541853, -0.4864220381446272, -0.5259537136583357, -14, -0.48933478618529186, -0.501706394219289, -14, -0.5235378294027251, -0.4826582221321347, -0.47816459985034804, -14, -0.47977211930424934, -0.4916746057901632, -0.47907239375443456] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1824  total reward: -5099.590868543773
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8712184260346684, -0.9389979214896615, -0.7478532760368418, -0.5931906843367123, -0.551590644610109, -0.5570044144754263, -0.6114450351032422, -0.5360287676881609, -0.5335673678172929, -14, -14, -0.5465409238512847, -0.5768857597882074, -14, -0.5758645752603727, -0.5326064479714022, -0.5272621884084715, -14, -0.5306206200034421, -14, -0.5259333223505538] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1825  total reward: -5100.627033764434
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8046349983506291, -0.9331231918129768, -0.7281313378668631, -0.5799345678153742, -0.530813929305634, -0.5378844264212668, -0.5688212682449894, -0.5235150011419094, -0.5152425257856266, -14, -14, -0.528562242144959, -0.5580113396964761, -14, -0.5568642919365387, -0.5154392992059063, -0.5069824426850477, -14, -0.5152122154472821, -14, -0.5102318983109734] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1826  total reward: -5101.863123607115
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1520129280702958, -1.5311515829697568, -0.9434839261004954, -0.8965384063964807, -0.7557111431975067, -0.7268806069870875, -0.7929775242271829, -0.7370760112747378, -0.7769730290979158, -1.1351240573183503, -14, -0.7374173153584083, -0.7451361480890086, -14, -0.7370760112747381, -0.7315712795507358, -0.7541338445500831, -14, -0.7295262249631984, -0.7308248590995164, -0.7291073999958825] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1827  total reward: -5103.190846676621
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1941456324206534, -1.120338423055229, -14, -0.7778013610119793, -0.6431526800959775, -0.5940651418271196, -0.757667050293566, -0.5969877130267215, -0.6281094761659357, -0.6487920346508028, -14, -0.6157223810021735, -0.6391793305331227, -14, -0.5969877130267228, -0.5988110959375441, -0.5953295713502735, -14, -0.6037156941964198, -0.6423998019879447, -0.6008424625188119] argmax 5
Action chosen: switching off line 5
  Simulating cascading failure
  ok
timestep 1828  total reward: -5104.341777330559
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2352180764564147, -0.8913800010675836, -0.6625527588182102, -0.567489891591026, -0.5871278849291759, -0.5857458406379109, -0.6933348650357739, -0.5732859458014459, -0.56250645789132, -0.5699851618589958, -14, -0.5682880515619958, -0.5868639381158399, -14, -0.6040874283043126, -0.559442471240903, -0.5502072085359511, -14, -0.5587804948527175, -0.5811570590633476, -0.5568655121117962] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1829  total reward: -5105.382927993633
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6599061509254824, -0.9699084660642983, -0.6090369269873784, -0.532777648917277, -0.48699279669086926, -0.4978465259935028, -0.4673636361272471, -0.5141048176941213, -0.49140157539309426, -14, -14, -0.5038886470006828, -0.5250192979765412, -14, -0.530603050901675, -0.47014549527531097, -0.4509343858066836, -14, -0.4945736407864914, -14, -0.4909434545370053] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1830  total reward: -5106.199871108953
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6438832879688039, -0.6394159235778849, -0.49693641756573304, -0.41215684977075023, -0.38731720138833425, -0.379633700506105, -0.42934515375489063, -0.3671036788099343, -0.3756059762712195, -0.41357619657055206, -14, -0.37471664041814695, -0.3854843578182343, -14, -0.40505783788103156, -0.36847722440944825, -0.3676940340430271, -14, -0.3668015350977984, -0.37855291102408267, -0.3660087295133514] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1831  total reward: -5106.946183614703
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6368260933444546, -0.6916847129836076, -0.520231018537726, -0.4441334331407174, -0.401315569427085, -0.38810528695481306, -0.4396937071275968, -0.37482260293472697, -0.39521151272673405, -0.45576635409558686, -14, -0.3895014690575383, -0.40009653032818987, -14, -0.418201148793316, -0.382963176125182, -0.38230862698315793, -14, -0.3810371724372682, -0.389809107904557, -0.38030377623666156] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1832  total reward: -5107.9069175862105
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2963613362475026, -0.9199604578202002, -0.6826888077034096, -0.5996896265453524, -0.6176686021926144, -0.6073701432783107, -0.7525037091865003, -0.5614179064839934, -0.5910524745247047, -0.5916985761538188, -14, -0.5952320268929362, -0.6055614733303295, -14, -14, -0.5887537657781139, -0.5902558049969822, -14, -0.5865032455219985, -0.591607802726558, -0.5859113685731722] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1833  total reward: -5108.980227135856
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8650805060319049, -0.9123417674235613, -0.7321997164669706, -0.5876904733155628, -0.5403169566067497, -0.5368818463545724, -0.5918880572634595, -0.5132159484978462, -0.5234566608063282, -0.5990040436163792, -14, -0.5231344629125625, -0.5359932646529022, -14, -0.5593653597176013, -0.5158931517591436, -0.5173368749992823, -14, -0.5127365665136031, -0.5197061624574236, -0.5118916431612794] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1834  total reward: -5109.816681140228
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5592789039685029, -0.5630679186127, -0.43618608250939617, -0.36953425585786315, -0.3433532540409414, -0.3333437919178798, -0.3818534319282136, -0.327092194923351, -0.33272294804879804, -0.36249951789072404, -14, -0.33319779232050967, -0.34453839162462907, -14, -0.36188161386883766, -0.32702147084718486, -0.3260318889563906, -14, -0.3256152050341199, -0.33507871448462706, -0.3245623612105968] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1835  total reward: -5110.569090634758
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9641024485920292, -0.675946502843256, -0.5159359224332308, -0.43296575072517895, -0.4502070618584894, -0.4582788540047291, -0.5351196860458247, -0.4484286206312974, -0.4294198268256454, -0.43276266505059646, -14, -0.4362847898694162, -0.4474113349642289, -14, -0.4593068039659021, -0.43023260756709913, -0.4225800824560083, -14, -0.42846291780945917, -0.44047952044717686, -0.4278471333196826] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1836  total reward: -5111.363952377633
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6252966139279365, -0.650939966162109, -0.5260471427275445, -0.42061361149395304, -0.39186356389573457, -0.39290662115053787, -0.44513045549173635, -0.38495085186061745, -0.3762400458348703, -14, -14, -0.3832594246131175, -0.3997390772565281, -14, -0.41336894168095106, -0.37769213293422793, -0.3754177796790158, -14, -0.3748805489958549, -14, -0.3722816604190036] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1837  total reward: -5112.103604598111
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6461463232274187, -0.6662365120727255, -0.5162098364998831, -0.40929615004199876, -0.3871486045837359, -0.389906799481919, -0.4344457539236589, -0.37560132154267234, -0.3701447898847252, -14, -14, -0.3786980077487862, -0.3959839513080419, -14, -0.3949106327676627, -0.3723812768320639, -0.36853626250140636, -14, -0.37014423753958253, -14, -0.36737056005869395] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1838  total reward: -5112.961178402401
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8095858132136645, -0.9120107633999035, -0.6498608233849575, -0.5498677101108825, -0.5113800091273428, -0.5036554967013483, -0.5484670484410451, -0.50303095589034, -0.4962201735250423, -14, -14, -0.5075861386767734, -0.5317620740958738, -14, -0.5399114785347662, -0.49528171940002524, -0.48852055022173807, -14, -0.4937067096209956, -14, -0.49020324423157563] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1839  total reward: -5114.122378167201
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0526982745536173, -1.315564320921062, -0.9089089244347982, -0.7804560404158768, -0.6961075433842011, -0.6838976589788998, -0.7188568389684267, -0.6669556416995227, -0.6946584266144656, -1.0018005586565975, -14, -0.6775447162688655, -0.6818287698647233, -14, -0.7386849087811459, -0.674362385633388, -0.7040500245564398, -14, -0.6726680029478468, -0.6711784092901298, -0.6726792145777395] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1840  total reward: -5115.1709707540795
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6619225587045091, -0.6496317719751193, -0.5552679126611425, -0.43185718087239966, -0.4043611134390803, -0.40864055186122855, -0.45873320721675354, -0.37678418309030504, -0.38096016883685646, -0.4132295992954805, -14, -0.3886762342767426, -0.3953162566982086, -14, -14, -0.3819541753429145, -0.39429970187024016, -14, -0.3822833218797503, -0.38540681577482533, -0.38163694517933366] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1841  total reward: -5115.715890496778
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.17120411192478344, -0.16993593398259949, -0.22160252819443083, -0.20075101914035748, -0.1672757739038201, -0.16841682078795894, -0.16991576521030688, -0.20585411009601948, -0.1688777435095368, -0.17260026369989057, -14, -0.17633532338504448, -0.18665084728333012, -14, -0.22901760026140733, -0.16829863497716094, -0.16792299659443993, -14, -0.16937717378621384, -0.18278067822723756, -0.1681355596079525] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1842  total reward: -5116.231415057647
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.531697743611682, -0.5148760477456752, -0.469137111344382, -0.40512356106751185, -0.32815560864455695, -0.3528972697672515, -0.39768815858861417, -0.34756921033162325, -0.35584909654616315, -0.39964438157700305, -14, -0.3566163435400632, -0.3695867069909378, -14, -0.37263281975025475, -0.35100669269309304, -0.3443807016119334, -14, -0.34950580711810403, -0.36113783222662565, -0.34824878696530936] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1843  total reward: -5116.893228562023
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5898282175725683, -0.5872831043411155, -0.4544919269555476, -0.37734558270343693, -0.3534582920798289, -0.3456331708178554, -0.3928876095075245, -0.3336362970093123, -0.3421749195326399, -0.3784123300913124, -14, -0.3417990295513872, -0.35270818617890765, -14, -0.36556508483181005, -0.3361173681926832, -0.3363329873629673, -14, -0.33469336574511044, -0.34449188069987713, -0.3336578957320277] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1844  total reward: -5117.797891352744
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0045980992955463, -1.1003509167941419, -0.762219753147396, -0.6913072318349118, -0.6083402409498646, -0.5727264092662145, -0.6968021638361092, -0.5736060461905113, -0.7540138995024065, -0.6468663032744507, -14, -0.5908574105193509, -0.6122721316493507, -14, -14, -0.5692021845307689, -0.5705796654998205, -14, -0.5772421086598654, -0.6220076197919409, -0.5710264937106232] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1845  total reward: -5119.045350888209
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1502933736823155, -1.1746331056060693, -0.9906258428192279, -0.7966992113707891, -0.7209232625120476, -0.7089908638849801, -0.8178260308491896, -0.6797003848594465, -0.6798585050593415, -0.71713801790105, -0.7014626308551436, -0.6929772178622968, -0.7027096136302509, -14, -14, -0.6776819900025217, -0.6874332906246333, -0.689578932955184, -0.6796114002419321, -0.6866470279759499, -0.678257350934674] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1846  total reward: -5120.424935529343
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2072875580434173, -1.235511885148348, -0.9851420602431955, -0.8037523893882168, -0.7429776748863804, -0.7315139275997298, -0.8350497088207325, -0.7051617647266062, -0.715441438655819, -0.7810255960848032, -14, -0.7183662288600537, -0.7340371651461514, -14, -14, -0.7020920270427415, -0.7264863903148585, -14, -0.7042779915488178, -0.7148979624766227, -0.7019026511320279] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1847  total reward: -5122.200935454541
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8325865291575385, -2.045899604088944, -1.5446480800589732, -1.31656785237836, -1.1430440446155672, -1.0925754308204467, -1.30903195489571, -1.0797452471342661, -1.3622248186494392, -1.2242350957309869, -14, -1.1079178385640291, -1.141907938249042, -14, -14, -1.0716192153025275, -1.0745636288729654, -14, -1.0831699201565137, -1.14691967297751, -1.0740972740653951] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1848  total reward: -5124.042154256397
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3156004807644082, -1.373655213970827, -1.026125168776572, -0.8959341572209618, -0.8153450931412528, -0.7804866693376539, -0.9098625194313905, -0.77672530515216, -0.7815581582036903, -0.835984399331394, -0.7987877053995666, -0.7890747776432714, -0.8020753732345395, -14, -14, -0.7702425882929078, -0.7913891420634078, -0.7804459295857369, -0.7718274202070852, -0.7815578750780257, -0.7695995865544661] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1849  total reward: -5125.669793220698
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.482543518062398, -1.496344743124701, -1.2126182042908025, -0.9941369954075715, -0.9114551121672341, -0.8909812637189739, -1.0304737625451543, -0.8693403253383662, -0.8734716219399701, -0.919723081081497, -0.8945455654086543, -0.8773371073202115, -0.8948777105442227, -14, -14, -0.8577212002070602, -0.8740685919048219, -0.8749890021316287, -0.8615135638651108, -0.8781434951116281, -0.8580393777458465] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1850  total reward: -5127.419846275881
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5125628410555334, -1.5648808025244205, -1.2529573145066166, -1.0237970259744458, -0.9432103400970805, -0.9291676771085896, -1.0552497996348817, -0.8899649784642024, -0.8999820706938555, -0.9962777495421264, -14, -0.9088311541449484, -0.9247405656091771, -14, -14, -0.891847551963964, -0.9283464306406004, -14, -0.8944563476542587, -0.9058007703877152, -0.8923318549760725] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1851  total reward: -5129.157521659581
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4440260900142603, -1.4622130504438506, -1.239748654433417, -0.9749167906001277, -0.8980745152905206, -0.8987869800880292, -1.0039683445334797, -0.8533900639201263, -0.8646853122813501, -0.9390380313766091, -14, -0.8660559335738698, -0.8917796488142118, -14, -0.9238325291304966, -0.8533606263790467, -0.8473126415789283, -14, -0.8501019811908663, -0.8724478274105316, -0.8477104052363952] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1852  total reward: -5130.6893346314555
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1313377669953733, -1.2255464762058748, -0.9646032235194304, -0.7675104558588289, -0.7167008077884844, -0.7244875394828993, -0.786589017766453, -0.6990147336600274, -0.693665577876234, -14, -14, -0.7090526940072261, -0.7476869714168375, -14, -0.7496757579637249, -0.6928580682735662, -0.6850829275805903, -14, -0.690898797026281, -14, -0.6845003302950087] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1853  total reward: -5132.063518894053
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2035258604009622, -1.2454911003264044, -0.9759026583583368, -0.7670154322829819, -0.7260484551437704, -0.7358338310837331, -0.8111260664760651, -0.7074713639241215, -0.6936892525732221, -14, -14, -0.7130607517342517, -0.748747494946611, -14, -0.74059901624616, -0.6988467581826635, -0.6908243364433978, -14, -0.6954123909377604, -14, -0.689683932302832] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1854  total reward: -5133.384302065113
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0465055494374558, -1.160023124580869, -0.8723100980032317, -0.7124549483164232, -0.6604227354885968, -0.658078795194641, -0.7201971781607519, -0.6428030817033544, -0.6389845249976677, -14, -14, -0.6563442454281704, -0.6945786067254192, -14, -0.6854771002155674, -0.6385426221574051, -0.6292162896570153, -14, -0.637185724636342, -14, -0.6310992387565151] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1855  total reward: -5134.684843190829
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1932312062846393, -1.1823586591159156, -0.9065870476263573, -0.772183329268006, -0.7137974466461661, -0.6871869086842609, -0.8068577174684942, -0.6701667676509602, -0.6892257235453124, -0.739269625454648, -14, -0.686602300349973, -0.7100955435357641, -14, -0.7341066857270662, -0.6749849118203471, -0.6680045183183246, -14, -0.6738678532652919, -0.7000711620597856, -0.671324836058999] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1856  total reward: -5136.107445220672
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2443468139973783, -1.3837448351894142, -1.0378649832648263, -0.8497818382823356, -0.7887804469910001, -0.7862990970959166, -0.8562916921795588, -0.78026736350761, -0.7594673191427675, -14, -14, -0.7802434138151666, -0.8176792829835315, -14, -0.8238615842888787, -0.7627364699656988, -0.7525175407040761, -14, -0.7603254377877345, -14, -0.7545975115247] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1857  total reward: -5137.626545007529
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2973716991573252, -1.2976089720737132, -1.1027442620686536, -0.8739855820393195, -0.8109056380934709, -0.8113945678980977, -0.9055378581086796, -0.7829733766567761, -0.7782856590217134, -0.8510268160239675, -14, -0.7837906846966923, -0.8056920537940052, -14, -0.844292342253597, -0.7731594726151345, -0.7703363290804783, -14, -0.768220709505583, -0.785472066833753, -0.7665822461528358] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1858  total reward: -5138.786656909819
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3993576410823135, -0.39581860531552954, -0.5189789721783024, -0.4625206365200262, -0.39229461345465644, -0.3958880992984694, -0.398063700085273, -0.4966900685361566, -0.3933314368069557, -0.41034127164482254, -14, -0.41162845736899883, -0.4354459516637767, -14, -0.5286971038138075, -0.3946991879572432, -0.39362835316281247, -14, -0.3966158018273125, -0.4218741339651065, -0.3935296561370739] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1859  total reward: -5139.786711983835
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9212886705439304, -0.8804446640039567, -0.8310078891557937, -0.6965068297959081, -0.5736182161099865, -0.6235035642892998, -0.6897208803703624, -0.6160601258424419, -0.6177699814535274, -0.686140544364116, -14, -0.6218751082056643, -0.6425767712783342, -14, -0.6582604501897172, -0.6130768217308675, -0.6018051378689939, -14, -0.6094847254297183, -0.6285329733690517, -0.6077604605615359] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1860  total reward: -5141.091760945288
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2844911313311926, -1.2568240639248773, -1.0629197084175253, -0.8314154785714047, -0.7763323286741352, -0.7795741357579369, -0.8739041819520936, -0.7356106160754022, -0.7456772197402809, -0.8038502762918732, -14, -0.746763791661566, -0.7669609256348242, -14, -0.7930329948431349, -0.7359214854461598, -0.7272105262149857, -14, -0.7329154994297082, -0.7522489381671387, -0.7314307453432871] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1861  total reward: -5142.48130113926
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1243609716062315, -1.1805685284679472, -0.919651529691483, -0.7522168789758238, -0.697833223319781, -0.6904571283458892, -0.7929678905678373, -0.6750174123810792, -0.6731862047073801, -14, -14, -0.684620316846927, -0.7186209690657129, -14, -0.7295963010381774, -0.6714769286616372, -0.6674853116366376, -14, -0.667782778598447, -14, -0.6623296677572602] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1862  total reward: -5143.8415746844075
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5372057108852408, -1.1466016947278002, -0.8274004693661402, -0.6980405185044146, -0.7320771679059987, -0.7483389216528387, -0.86087350436871, -0.7411661695980964, -0.6974383919298212, -14, -14, -0.7197009107662068, -0.7559303443334037, -14, -0.7563842866619607, -0.7086821178607944, -0.7032612037090011, -14, -0.7042899558493736, -14, -0.6979438773898563] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1863  total reward: -5144.964009823104
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6925188195762333, -0.7724690178298609, -0.5668108709870223, -0.4719964329739682, -0.4425828774846488, -0.44051456898073327, -0.4723568789086703, -14, -0.420341625585326, -14, -14, -0.44371897002934296, -0.4705294116381402, -14, -14, -0.4327398381967784, -0.42964838332539135, -14, -0.4290128910768267, -14, -0.424996746766596] argmax 8
Action chosen: switching off line 8
  Simulating cascading failure
  ok
timestep 1864  total reward: -5145.825038641666
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7047328081748584, -0.8467352724257077, -0.5952520350646439, -0.5047182362891971, -0.457637996539124, -0.45099092013124, -0.4844436217697382, -0.4522764144676366, -0.44321494014174323, -14, -14, -0.45743722322703406, -0.4838241802349401, -14, -0.473487550783734, -0.4437237318183774, -0.4340746171034763, -14, -0.4450623593195493, -14, -0.44068719297673137] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1865  total reward: -5146.619227524192
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6101858322166683, -0.6295766980089899, -0.4989935414259402, -0.4119338198407076, -0.3803724682732707, -0.37341711078516054, -0.41962988460338246, -0.35763083390879497, -0.37258113506264146, -0.41242517253850425, -14, -0.36937840174693437, -0.38121143651593814, -14, -0.40007374595146106, -0.36246881212874327, -0.36067355300571263, -14, -0.36116135836188273, -0.3714537423877977, -0.36011426542248853] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1866  total reward: -5147.394426288818
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8917266639315118, -0.624585586621121, -0.5040643504558822, -0.4229282988715785, -0.43714542510264875, -0.4494858022434296, -0.526576539244649, -0.3960828197011391, -0.42412442439046094, -0.4162214946406299, -14, -0.42476046607429796, -0.4329094313467784, -14, -14, -0.41962969655215715, -0.42264465244994354, -14, -0.4180956736249806, -0.4233673049459228, -0.41756793071740567] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1867  total reward: -5148.197213101044
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7186716656774104, -0.7093452855267693, -0.5675672720857617, -0.45596820169209235, -0.43042340571270654, -0.4285088544791715, -0.47691542070260257, -0.40878988059356663, -0.41505495379326246, -0.46008505269735794, -14, -0.41640852223401814, -0.4303969751226548, -14, -0.4433236608378058, -0.40988590816636933, -0.4132954051659162, -14, -0.40830698689610456, -0.4179308836496954, -0.4067039925246857] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1868  total reward: -5149.1561707412075
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9542470864447686, -0.9691007107463102, -0.7687698136448322, -0.6359217791275684, -0.5854394095487604, -0.5716551527327485, -0.6542633582606462, -0.5525482837618888, -0.5665575110236153, -0.6214888247124298, -14, -0.5637235955032471, -0.58078482203076, -14, -0.6062559060939441, -0.5559937484069131, -0.5508587564936256, -14, -0.5539856979168232, -0.5695336300363546, -0.552253647639464] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1869  total reward: -5150.162064650467
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.47431235580743863, -0.46938627476285927, -0.5728803253285086, -0.5101637968787921, -0.4464998961903735, -0.4616032667168809, -0.45404955621028614, -0.6148428700909936, -0.4533149438433672, -14, -14, -0.47786316992511757, -0.514764296100821, -14, -0.6105689196680739, -0.45698826196214143, -0.4494074601904028, -14, -0.46131398321934663, -14, -0.4550351527653968] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1870  total reward: -5151.427671613574
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2119393957623443, -1.2371189525328723, -1.0960101321072537, -0.935492109883203, -0.7852919883260251, -0.8376256116582309, -0.9260636501612923, -0.8262441988589174, -0.8336325011078782, -14, -14, -0.8479817321869855, -0.8905352863114618, -14, -0.8853597483805415, -0.8344854234817187, -0.8271960676209247, -14, -0.8256861553891549, -14, -0.8191070669166485] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1871  total reward: -5153.51332509932
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.0407966125167163, -1.4259137778179956, -1.369682289540006, -1.5093814970951682, -1.5745467300409992, -1.3618930961645261, -1.3006909555495814, -14, -14, -1.333919511867173, -1.3807579788059672, -14, -1.3975142503431939, -1.319639298107027, -1.3109336748022622, -14, -1.3071769456113136, -14, -1.3003614974196944] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1872  total reward: -5155.794345744029
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5884350851287843, -1.7684602729970287, -1.350825199246209, -1.1090993306701638, -1.0245437263603452, -1.0205608940627318, -1.1174639171255076, -1.0264608864073528, -0.9849397189221268, -14, -14, -1.0155891892081004, -1.0690159525206335, -14, -1.0816322064381523, -0.992702021808597, -0.9781034161808992, -14, -0.9892525730288373, -14, -0.9806591472898746] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1873  total reward: -5158.093154639575
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.7438153176631148, -1.5367191798278976, -1.350312252398972, -1.3328236445003099, -1.3750611523093705, -1.323803744811179, -1.3618917482857689, -2.029376155494286, -14, -1.3316999074036693, -1.3398254548210666, -14, -1.5029745306068287, -1.3220397302422429, -1.4198623005852162, -14, -1.3206632133599048, -1.318547455736503, -1.320705479365529] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1874  total reward: -5160.440051157719
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.833155126943585, -1.7659107634690616, -1.420712283167715, -1.1717173613137284, -1.0932469015403097, -1.0690650850737846, -1.3253208326500725, -1.026177871581159, -1.073181706646844, -14, -14, -1.0443520586214925, -1.0572781676618679, -14, -1.1611629858739723, -1.0345458303109387, -14, -14, -1.0290635175302052, -1.0091056305043, -1.0283490624068394] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1875  total reward: -5162.350476116591
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5141669145303447, -1.5345019382914593, -1.3267444046804198, -1.0402839754013662, -0.9545313446567205, -0.9567936099531489, -1.0698220866863408, -0.905439381258165, -0.9212917783694652, -0.9919980691324863, -14, -0.923154478958807, -0.9546781451203695, -14, -0.98523029599345, -0.906875933175635, -0.9031634725315516, -14, -0.9045963180814508, -0.9361858123652934, -0.9013193283685492] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1876  total reward: -5164.115128409825
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4764288897021092, -1.5245062724395404, -1.213033905817572, -0.9841609973245452, -0.9120251541404717, -0.9022761578795101, -1.0030986454701094, -0.8634807032649553, -0.8849815937643449, -1.0035067257344852, -14, -0.8828930791914295, -0.9075575796000085, -14, -0.9458649277698572, -0.8701742622666065, -0.8716282163638887, -14, -0.8654307789220087, -0.8809698065696946, -0.8633329648642475] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1877  total reward: -5165.6598445913705
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1021927080131146, -1.2027184939755393, -0.9301895893610408, -0.7918032521464327, -0.7163872664562235, -0.6968140716805744, -0.7806076745018918, -0.6784525675274131, -0.7063124271411712, -0.7927578950618429, -14, -0.702239366769225, -0.7278870073847901, -14, -0.7693859501556851, -0.6860758571884896, -0.6906498244007474, -14, -0.6839391957316926, -0.6994220127196361, -0.6813832166820368] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1878  total reward: -5167.00404291224
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1623379546954447, -1.1826963903232885, -0.8898313218121039, -0.7628517087134471, -0.7054504016991553, -0.680096134829187, -0.7951552197214184, -0.6622096620617862, -0.6695945770585141, -0.7374975474548952, -14, -0.6792139432635578, -0.6891787716155564, -14, -14, -0.6658051199537678, -0.6836222991495826, -14, -0.6665124421805653, -0.6725241045497152, -0.6657457533416242] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1879  total reward: -5168.357727359982
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1444187682685114, -1.1874625664054825, -0.9926801269819989, -0.7941563219144868, -0.7296441010887321, -0.7271928114157572, -0.8055313768208343, -0.699689440952066, -0.705938196934208, -0.7769904828540795, -14, -0.7082730719023705, -0.7300426097839187, -14, -0.7661193585946489, -0.6969979844275561, -0.6976534410156853, -14, -0.6934275989482551, -0.709493344334183, -0.691474785680125] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1880  total reward: -5170.048290220568
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7309179774454988, -1.751458988815646, -1.4157392425112156, -1.1341974473484873, -1.0569974301690201, -1.0514363795903034, -1.1693976555895396, -1.0099256757757287, -1.0174756703573922, -1.1382950027555299, -14, -1.018439177033205, -1.0446311223820333, -14, -1.0933340073823803, -1.006965535569048, -1.0042715445185826, -14, -1.001343297546559, -1.0175962468012307, -0.9990880749059926] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1881  total reward: -5172.265056106972
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.4490939858985685, -1.2351464127947656, -1.2839622376026392, -1.2841459800026587, -1.4793242553071952, -1.2645874764317913, -1.2249190811191506, -1.2800777852039316, -14, -1.2372875627408932, -1.267294620548665, -14, -1.3143137166768082, -1.2270514584970313, -1.2124725192475863, -14, -1.2202976188251093, -1.2480123841501847, -1.2176778114987523] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1882  total reward: -5174.276248457935
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.248127217186073, -1.4359097458382772, -1.1013373100854487, -0.8950785771730891, -0.8288257220634889, -0.8362934317126616, -0.879254787124127, -0.8417807419130552, -0.8011758654850063, -14, -14, -0.8300076603665469, -0.8774211505245492, -14, -0.8841572019137329, -0.8056693810744009, -0.7898113238990289, -14, -0.8062720826254008, -14, -0.7987198317152431] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1883  total reward: -5175.860130065937
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3547156926612156, -1.3387372627903635, -1.1618284392653955, -0.9080175640720739, -0.8415806681781665, -0.8461881838479448, -0.947385458288593, -0.8052736937838002, -0.8087031055150615, -0.8621665696677326, -14, -0.8099998577946382, -0.8337406525916775, -14, -0.8722734278285021, -0.7989754732181499, -0.7879310880416232, -14, -0.7963214884506724, -0.8163790966030198, -0.7940702841021624] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1884  total reward: -5177.520912987558
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.532167959381075, -1.6203974832464947, -1.2155167254005477, -0.9718305024449876, -0.917996609990927, -0.921483866096169, -1.0123738785329874, -0.8793204182067017, -0.8846765202903192, -14, -14, -0.9017941603087712, -0.9488215791851194, -14, -0.9284926188624871, -0.8828034191924753, -0.8730486508427618, -14, -0.8808947115776673, -14, -0.8728518335799654] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1885  total reward: -5179.34241681189
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7234648339904557, -1.7867304567109195, -1.363240540215941, -1.1460578410788789, -1.0171052780099945, -0.9708505019381388, -1.25366543917483, -0.9513108283037321, -0.9911861583676268, -14, -14, -0.9758464493571988, -1.021064204368605, -14, -0.951310828303732, -0.9537295390190599, -0.9584154109821358, -14, -0.9565613544740289, -14, -0.9486519907521394] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1886  total reward: -5180.896505740852
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0024628908975157, -1.111313311198007, -0.8288008934810585, -0.6785490225217461, -0.6326357256578214, -0.6313208152104978, -0.6842471609781332, -0.6196602442249088, -0.6120909217107239, -14, -14, -0.6287396686587959, -0.6621406463210212, -14, -0.6604848544725155, -0.6119997196226482, -0.603196271848984, -14, -0.6104455522359276, -14, -0.6054369382102305] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1887  total reward: -5182.004834436354
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8924891898571315, -0.8870685545074106, -0.7103589853696592, -0.5797565526460805, -0.536755641831105, -0.5261382641169281, -0.6045925313240543, -0.5023474666578258, -0.5185483887841235, -0.5634481535300002, -14, -0.5168830424396482, -0.5319867833022826, -14, -0.5466780129130286, -0.5081982503752903, -0.5029207064652309, -14, -0.5062537509106732, -0.5237354178459395, -0.5051324236525169] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1888  total reward: -5182.957480622432
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7754709205466771, -0.7835778748337698, -0.629579662888077, -0.5208470259243234, -0.4778821031321116, -0.4660553814784275, -0.5450080759946431, -0.4457247877969045, -0.45009232627674867, -0.4851775942388675, -14, -0.4592528713416574, -0.4667017315755533, -14, -14, -0.45049005448774504, -0.4619262023987409, -14, -0.45086677700137306, -0.4569067795249742, -0.45029871941904825] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1889  total reward: -5183.750806356858
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5568140861418005, -0.5913737991708592, -0.49607820166251687, -0.40124267446796735, -0.3656675524496232, -0.3634767710368826, -0.4009380698274576, -0.3584429263426041, -0.35314366976569217, -0.3889024165557141, -14, -0.355141751662725, -0.3645755399186251, -14, -0.3916869781000858, -0.35052885572936726, -0.3513195633375511, -14, -0.3483124412034599, -0.35515727972481276, -0.34760094662968344] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1890  total reward: -5184.454209968849
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6088786454532907, -0.6206982639037267, -0.48554795213545743, -0.4089372576563423, -0.3766370105741217, -0.3658144150152903, -0.41962609725664335, -0.3601912230892971, -0.3635633895880228, -0.3973487613464852, -14, -0.3641503106807773, -0.375731431829561, -14, -0.3954923285565128, -0.35845098758175026, -0.35611504119098575, -14, -0.3569202964523189, -0.3649244649681099, -0.3558026653609151] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1891  total reward: -5185.360199280753
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2085497420434854, -0.8770368163680995, -0.6646174614367812, -0.5597399906530062, -0.5795370825815537, -0.5854902297249139, -0.6802860926941113, -0.5760162944596094, -0.5528963819727714, -0.5663353118947717, -14, -0.5604290836623957, -0.5763058348571293, -14, -0.5957183981963002, -0.5542745844636427, -0.5451110005834461, -14, -0.5516420841010614, -0.5654595576002418, -0.5501866465428017] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1892  total reward: -5186.403135290226
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8429807531459481, -0.9136847403225345, -0.6734014826020108, -0.5617425135339749, -0.5224793170833268, -0.5144252200854967, -0.5771143291919628, -0.5104679670371054, -0.5024856866121058, -14, -14, -0.5171336990767774, -0.5463512721474632, -14, -0.5417692486228121, -0.5041731437274963, -0.4975967772393516, -14, -0.5024717497867448, -14, -0.4978250088891188] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1893  total reward: -5187.6570581949145
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.363946372521532, -1.4538929545020471, -0.9931415404854527, -0.9344753890082022, -0.8114406259327814, -0.7555185983231363, -0.9394439720588865, -0.753765184629962, -0.8000507257571093, -0.8578177645316349, -14, -0.7781912757473227, -0.8115781904426302, -14, -0.753765184629962, -0.7556605227683433, -0.7498239011170557, -14, -0.7606846436093225, -0.80007203456385, -0.756326127450484] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1894  total reward: -5189.630919466614
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7642385242062613, -2.4352345989794717, -1.5609212895292393, -1.3320926431659115, -1.231358359589117, -1.252603736186913, -1.188190758210614, -1.2677113914676978, -1.2263463870969227, -14, -14, -1.2554399353286745, -1.302669067494921, -14, -1.3094958752561623, -1.1909397662729915, -1.1483565245500453, -14, -1.2315003378324154, -14, -1.2240373705820562] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1895  total reward: -5191.8681949220945
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.3053559867672269, -1.1048614258251, -1.149451281838139, -1.1523577090871013, -1.3261940436356396, -1.1098893182119887, -1.1006697064870437, -1.140050769411098, -14, -1.1077538646278777, -1.1356581807054797, -14, -1.1683381453787363, -1.0952806936073407, -1.0793067859130505, -14, -1.0912284766983198, -1.1242059897372538, -1.088918930930689] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1896  total reward: -5193.885357827491
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.5060880057082398, -1.7116007415227297, -1.2644593406340578, -1.0629165245010168, -0.9777091417313795, -0.965636046781188, -1.056225087149899, -0.962576490274162, -0.949252913401954, -14, -14, -0.9764680389566742, -1.0393767146169375, -14, -1.0328757488200755, -0.948187474991805, -0.9323209314835829, -14, -0.9486437251448472, -14, -0.9378561194835144] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1897  total reward: -5196.183782217424
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.9514955429126122, -1.7006615747588993, -1.4673458706354388, -1.3807973014270256, -1.7127304988060124, -1.3571082258115252, -1.429541210499093, -1.5295177667985103, -14, -1.3985094315509514, -1.4514525019316864, -14, -1.3571082258115255, -1.3646920455899914, -1.3528781282401918, -14, -1.3728182632154449, -1.4581574308804486, -1.3661034584487262] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1898  total reward: -5198.483130868177
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.55332036381483, -1.708640576133923, -1.3172819933189184, -1.0773485343746232, -0.9918833333661781, -0.985824635016613, -1.0974115542799858, -0.9698842162707302, -0.959523320177372, -14, -14, -0.9787779551003145, -1.0235096775753467, -14, -1.0451323536495618, -0.9591129472718445, -0.9497692747288954, -14, -0.952919336723125, -14, -0.9464705225136137] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1899  total reward: -5200.305491356998
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.390782808270066, -1.6136122883753101, -1.1882923696387884, -0.9935605190976912, -0.9108909862166318, -0.903353588497433, -0.9736980564087789, -0.8967503118344485, -0.8893146327978554, -14, -14, -0.909628900885708, -0.9598147983970837, -14, -0.9704937090223974, -0.8850785878422927, -0.8720585215567276, -14, -0.8837271863533889, -14, -0.8758899663071381] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1900  total reward: -5202.02400383273
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4262429417931426, -1.523661872403349, -1.1729876785398203, -0.9821249974348515, -0.8938463156125944, -0.8705548913376213, -0.9816927536722112, -0.8428425552630754, -0.8714938344731121, -0.9928956069053325, -14, -0.865720538989329, -0.8895909854968845, -14, -0.9311524498260603, -0.8527670395230911, -0.8516155523485947, -14, -0.8483843160358929, -0.8639951960479519, -0.8464539541759293] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1901  total reward: -5203.639961182595
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.329872481930237, -1.3612697853550506, -1.0567063693560812, -0.8923754229571199, -0.8193726685715528, -0.7937034909474078, -0.928740814839528, -0.7827728490234448, -0.8027463882435074, -0.8597920537976923, -14, -0.7936839482696386, -0.8148406967278952, -14, -14, -0.7731923756427592, -0.7916259657128264, -14, -0.7769644971062878, -0.7916629349660441, -0.7731147946001179] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1902  total reward: -5205.268606711386
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4597867922556442, -1.662778347995592, -1.1584834607902719, -1.0461915286729089, -0.9078731545059409, -0.8584272931408408, -1.0272822630832081, -0.8586719145495127, -1.1386985380285701, -1.006376930582002, -14, -0.8811349365402384, -0.9060065872310087, -14, -14, -0.8558395726425468, -0.8537935150490589, -14, -0.8627448128052132, -0.9293592760671061, -0.8555307341919712] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1903  total reward: -5206.85625866963
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.22039593688689, -1.3191217088183416, -0.9988887298076288, -0.8087583898855348, -0.7662042769469172, -0.7723036233528815, -0.8249906624650529, -0.710011994563133, -14, -14, -14, -0.7596488776266588, -0.7956559806714506, -14, -14, -0.7267391463098601, -0.7125152067830173, -14, -0.7390995284796499, -14, -0.7338584431951742] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1904  total reward: -5209.134953411516
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 2 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -2.449489310135201, -1.8533027051535034, -1.693497238436511, -1.6911788652320539, -14, -1.5725009711597004, -1.6297639414580916, -14, -14, -1.6011986145906958, -1.6475514542527174, -14, -1.5725009711597009, -1.561215432972323, -1.578768607107191, -14, -1.5755912049520804, -14, -1.5686827473230287] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1905  total reward: -5211.686766162542
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.672515566334767, -1.7348075030249788, -1.355594145169102, -1.117489027993905, -1.0428008083364935, -1.0294664582215238, -1.1237915276445665, -0.9953214556335765, -1.0102488948397061, -1.1841967078740452, -1.0215938659954715, -1.0248598554180848, -1.0769356024724983, -14, -1.0877978094367171, -0.9803614135286838, -0.984124939983975, -0.9981340632602939, -0.9989181651434459, -14, -0.9905973180529419] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1906  total reward: -5213.395153900179
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2113097857295645, -1.3331865732479222, -0.9633382695371678, -0.8024874105665816, -0.7589396650262494, -0.7551181928369451, -0.8086697417084127, -0.7569107757320649, -0.7308384873369963, -14, -14, -0.7592649182206639, -0.8075662374766065, -14, -0.7923412419894026, -0.7344169755133032, -0.7174004122080134, -14, -0.7358833639083605, -14, -0.7280263241083257] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1907  total reward: -5214.815491411661
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1680258872029914, -1.2385424944024452, -1.0275134052796677, -0.8108316187741994, -0.7415445113340668, -0.7430061917747083, -0.8132244317650018, -0.7050769897779124, -0.7185852796446647, -0.8070121797755873, -14, -0.7185640649052218, -0.7366716945260684, -14, -0.7676743805919873, -0.7082648595342498, -0.7100444454437325, -14, -0.7041321713404847, -0.7185090699520451, -0.7029370992744184] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1908  total reward: -5215.983203109584
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.47529787915044974, -0.4705789180207648, -0.6141347014158133, -0.5407058031342978, -0.4612445235922591, -0.46981927300226384, -0.46648208477802094, -0.5986753873776876, -0.46372710573461395, -0.4779611734923892, -14, -0.4852393014031583, -0.5081816918964064, -14, -0.6279024796301758, -0.4665849901578249, -0.47309730622776003, -14, -0.46726071661205, -0.48983939783382374, -0.46477459864801407] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1909  total reward: -5217.498438686445
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4994664561156856, -1.6217051011035333, -1.3618411888390944, -1.2031621397779189, -1.0265651850700865, -1.0667179482052584, -1.1385385499509089, -1.0564891747770817, -1.0806861420119889, -1.656013122364818, -14, -1.0652336259193331, -1.0767481832759538, -14, -1.1633889395385897, -1.0649647291112723, -1.094111951314111, -14, -1.0540512639333088, -1.048444255032622, -1.0539910532697772] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1910  total reward: -5219.2212563418625
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2051695184815354, -1.2120432181031828, -0.9774059660364571, -0.7890249916997477, -0.7365010177169783, -0.7304540820170888, -0.8157038176508424, -0.691933453253229, -0.7178103072618044, -0.7857354632869112, -14, -0.7114278539308853, -0.7326529317540752, -14, -0.76459070498629, -0.7007975389519352, -0.6969792804430912, -14, -0.6982481567650091, -0.7246760776182046, -0.6962524703466937] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1911  total reward: -5220.452296289583
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9417835010780039, -0.9005616113516789, -0.7432413801568926, -0.6069106659667312, -0.5713295178937972, -0.5641525047841102, -0.6540885507494766, -0.5260621919865995, -0.5375267241356158, -0.574556875489474, -14, -0.5479238604229003, -0.5564762921062185, -14, -14, -0.5397935463563651, -0.5522241498195031, -14, -0.5397897005957497, -0.5434176979951276, -0.5391064944664483] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1912  total reward: -5221.391772953804
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7015577693973328, -0.7142749000858417, -0.5772799912297405, -0.47681685708873944, -0.4377562478276089, -0.4282915453259744, -0.4893349164002674, -0.4188732748081818, -0.4217399330662779, -0.4588841711460807, -14, -0.4222742366385661, -0.43563940167093074, -14, -0.4569804870130876, -0.41664922488218303, -0.41390304816919266, -14, -0.414835368083046, -0.42606248943033215, -0.41341447223487243] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1913  total reward: -5222.144358343927
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5893010446474567, -0.5996378155026084, -0.4647260753143367, -0.38950497463714173, -0.3594338741466439, -0.3492761107402601, -0.40061330462136013, -0.33835094040629804, -0.3484218349207092, -0.3854217060087937, -14, -0.34827331682052937, -0.3597588172870117, -14, -0.3716485638750788, -0.34162895735526083, -0.3407525604166928, -14, -0.3401741264526641, -0.3490568751835967, -0.33917091788784726] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1914  total reward: -5223.116454519442
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.409400091707461, -0.9669613263589427, -0.8048418363356235, -0.6424760096203238, -0.6657766704374112, -0.7050940159278851, -0.8149521796149314, -0.6092627735141228, -0.6416131464091726, -0.6342504237503463, -14, -0.6402645255047452, -0.6489697301312913, -14, -14, -0.6367333328510035, -0.6302879360625723, -14, -0.6342661237565509, -0.6386809571589518, -0.6337452351096431] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1915  total reward: -5224.157824623583
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7614482143049934, -0.7600262992032804, -0.6168572230908432, -0.48775864916404066, -0.4576191189723914, -0.4581817819020408, -0.5070570340549626, -0.4309069340936643, -0.4429799087684479, -0.48675635395080125, -14, -0.4417370733005706, -0.45324240396522436, -14, -0.4693885661975713, -0.4348868985483689, -0.4309241866672439, -14, -0.4328740275338526, -0.4417929312739243, -0.43210733062632967] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1916  total reward: -5225.151261419153
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9524090180607776, -0.9740598717267708, -0.8111663001331951, -0.654719888583164, -0.5966475948214476, -0.5879898980732595, -0.6796478748613647, -0.5567884992553387, -0.5619903289253068, -0.6075690715875268, -14, -0.5711426126460176, -0.5805090746933999, -14, -14, -0.5627984105837043, -0.5760350532451526, -14, -0.5636127732134448, -0.5713572696510395, -0.5625298614769224] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1917  total reward: -5226.559762209401
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.48331218107952, -1.4259942752614954, -1.2423907375249506, -0.9728392503066339, -0.9050137274554619, -0.9071857866143931, -1.0321238377294446, -0.8642581074212603, -0.865512129991735, -0.9127108832985981, -14, -0.8680542664308866, -0.8937539180997017, -14, -0.9265745122726552, -0.8571342588907128, -0.8440923665303758, -14, -0.8541954574095304, -0.8845010457478291, -0.8517122909927378] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1918  total reward: -5228.304084715121
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.552461337231671, -1.6039569276854826, -1.244556326816815, -1.000436115024458, -0.9466871496000424, -0.9498628425631237, -1.058230395671602, -0.9248275539572339, -0.9101036666184957, -14, -14, -0.9301434554996989, -0.974719093619992, -14, -0.9889805898885923, -0.912649159199736, -0.9044440466942734, -14, -0.9072047150246595, -14, -0.9002301391887875] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1919  total reward: -5230.199403721538
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.624839269304509, -1.8128111723535982, -1.328127959428861, -1.1330005921396775, -1.0409205656646396, -1.0184810267632225, -1.1422750832785133, -1.0360753945334351, -1.0016798659180146, -14, -14, -1.0311930352198686, -1.0879941153842172, -14, -1.0999674314637815, -1.0079890338695239, -0.9931874276124004, -14, -1.0044942862841792, -14, -0.9950888672283971] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1920  total reward: -5232.573546177317
 Simulation with line 0 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 1 switched off
  Simulating cascading failure
    depth 0: 1 overflowed lines
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-14, -14, -1.797663839500164, -1.5829157490826922, -1.418409664616488, -1.3949914846038107, -1.4457373650921856, -1.3850019406248613, -1.423869005004198, -2.0968241989965937, -14, -1.3922947793437697, -1.4011695006557883, -14, -1.5726412685969455, -1.3832730449923796, -1.4714842746102066, -14, -1.3809346153884596, -1.3781471285889937, -1.3809550281682434] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1921  total reward: -5234.967924512195
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7916527113981418, -1.7524228265012332, -1.4323610079284694, -1.1822230530908686, -1.0831705979582356, -1.0530533833118902, -1.3334358520685132, -1.0104978939195395, -1.0601286890825348, -14, -14, -1.0317393853930805, -1.043930342514439, -14, -1.1327962919423695, -1.0217266655682373, -14, -14, -1.0168505838503197, -0.991680507446409, -1.0162312062881962] argmax 19
Action chosen: switching off line 19
  Simulating cascading failure
  ok
timestep 1922  total reward: -5236.99912327594
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6928879997682997, -1.8248207279035689, -1.4494534008791917, -1.2382303714423422, -1.0993370264522386, -1.0599418915215373, -1.2265182373470664, -1.0341599032019353, -1.0743598132483325, -1.169437717950538, -14, -1.064886578060142, -1.0989140805955502, -14, -1.1550009066763396, -1.0455824653214294, -1.0371353612934449, -14, -1.04240804890176, -1.0875768426966015, -1.0395182562992755] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1923  total reward: -5239.0852538132585
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7963354666596503, -1.837895603886618, -1.480405349136087, -1.2130156083409056, -1.1143807556854746, -1.093479727347239, -1.2604478590875492, -1.0543729455125708, -1.067073466075746, -1.1549205490827745, -14, -1.074763767043704, -1.0978819980044532, -14, -14, -1.0523742003300276, -1.084287706066336, -14, -1.0554279270094697, -1.0754613197250629, -1.051970634116217] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1924  total reward: -5241.294553001138
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.7661368589538708, -2.2793057725517842, -1.539075267582934, -1.336619524175164, -1.1902464104215602, -1.1727094583571411, -1.2166047036572794, -1.1628555878370133, -1.1974133590283984, -1.6916034158435795, -14, -1.1655360306348699, -1.1657968540266799, -14, -14, -1.1395704346522564, -1.2730339265177333, -14, -1.1572255384057526, -1.1615881119684155, -1.1573285537636528] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1925  total reward: -5243.149670762756
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.259008519967445, -1.2706621559500737, -0.9796531147589136, -0.8239726854759439, -0.7600411409958451, -0.7355854426498686, -0.8547647229892279, -0.7260975025267106, -0.7304418773863443, -0.7709029664626441, -0.7489668170303924, -0.7321228479194114, -0.7453225506400912, -14, -14, -0.7161490024315355, -0.7275645291744238, -0.7308223064287824, -0.7180222220015845, -0.7295922250624096, -0.7155473269649996] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1926  total reward: -5244.620035833759
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3037130839162092, -1.2796363063561305, -1.0758501583870892, -0.8718887579541442, -0.8025377859340157, -0.7887192980233471, -0.9155995992495761, -0.7530267628441215, -0.7542900777999317, -0.7970883469014926, -0.7819435620859073, -0.7711147497828914, -0.7826951066496449, -14, -14, -0.7541782606956899, -0.7697352653557265, -0.7655998580664487, -0.7565658420516564, -0.7656424848937207, -0.7548177440389074] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1927  total reward: -5246.107120879105
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.23601476947272, -1.2495214766312916, -1.0841668673886253, -0.8566171038790205, -0.7791617907435847, -0.7743725980677671, -0.8613492918820116, -0.7358748382351619, -0.7461322839296282, -0.783797830006717, -0.771925810227052, -0.7523824784862791, -0.7693155095954975, -14, -0.7904561609067157, -0.7291659748905871, -0.7389031892311878, -0.7518855041555083, -0.7357078301498451, -0.7546570002473425, -0.7340582825021976] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1928  total reward: -5247.656755463978
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3975009406376722, -1.3902374989933985, -1.1785486131003553, -0.9331010101628197, -0.8681498597147096, -0.8692835958979965, -0.9698460351053523, -0.8302525622707654, -0.8367486205059842, -0.889552919877153, -14, -0.8417603045375462, -0.8695952314026923, -14, -0.9036285272849284, -0.8260843102900802, -0.8217058661971017, -14, -0.8229076004399477, -0.8509264417357411, -0.8204686099813363] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1929  total reward: -5249.430864479022
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6248300693164148, -1.6405731348419934, -1.3905993784192388, -1.089808736287967, -1.009283212940629, -1.0141691811621922, -1.1236821228236693, -0.9674351416815145, -0.9695295467826421, -1.0510277365652512, -14, -0.971991774016846, -0.997026438436619, -14, -1.0423873184134516, -0.9607981530715923, -0.9524545962985721, -14, -0.955648160068023, -0.9782292408323953, -0.9536404050626435] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1930  total reward: -5251.124850568785
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2262128229699314, -1.331782408849281, -0.9877550195608846, -0.8144223369041501, -0.773029657245994, -0.7739233919100511, -0.8268076215484218, -0.7800000210678248, -0.7439445866550043, -14, -14, -0.7694875732567367, -0.8090032176060751, -14, -0.8192627144261375, -0.7484231493548524, -0.7356525409899939, -14, -0.7473648163168696, -14, -0.7415314934648952] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1931  total reward: -5252.163485092383
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3318119719978968, -0.318164897369318, -0.4195463064477189, -0.516308474963083, -0.2933723103728645, -0.3306106067249934, -0.31686165877231354, -0.30515798313161885, -0.342356733178258, -0.31981437787664524, -14, -0.33281516246242876, -0.3794674857043871, -14, -0.30515798313161907, -0.29197227808202325, -0.30680106117418837, -14, -0.3115285401558358, -0.415293787225478, -0.3029819826073322] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1932  total reward: -5253.27985493387
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3781997158993744, -1.4245253936572506, -1.1921659150425592, -0.9695858336829939, -0.8744269912093043, -0.8570495864655513, -0.9629954476539558, -0.8210863712810911, -0.8414285063850794, -0.8959767038053218, -0.8650193238725307, -0.8449219237013205, -0.8672230229110718, -14, -0.8917098670934214, -0.8185943245097144, -0.8334005724011798, -0.8447723246994207, -0.827451660281665, -0.8476910762228937, -0.8243975634056773] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1933  total reward: -5254.812979501782
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1976190419689865, -1.2873464910670427, -0.9717554256538251, -0.8363242041179286, -0.7549186340104489, -0.727356761354341, -0.8325338651218737, -0.7091463909727312, -0.7381614931514379, -0.8271812576358647, -14, -0.7333446616771568, -0.7575841034085083, -14, -0.7878518719133997, -0.7193431969201541, -0.7237046787045451, -14, -0.7167987514829385, -0.7411496430144725, -0.7145302434022617] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1934  total reward: -5256.202937619586
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4953127782884028, -1.1313782775350645, -0.777866750535191, -0.7010584622404878, -0.7202821303782655, -0.6933200597354287, -0.85085784045127, -0.6631312953180295, -0.6792653612981991, -0.6996710826437303, -14, -0.6910518272911361, -0.7018943944597704, -14, -14, -0.6823290537941092, -0.6868991921968204, -14, -0.6816074608805648, -0.6890718667420809, -0.6808117268314093] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1935  total reward: -5257.1510107186
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.29279138308169184, -0.29024887576391967, -0.36943301072734896, -0.33019451893751284, -0.28184686517401747, -0.2871858073212263, -0.28501807477371327, -0.3641831539590186, -0.2844701278357485, -0.288060358426648, -14, -0.29648252776893885, -0.3093267225319221, -14, -0.38956213389507005, -0.2863718304737354, -0.2925667366645886, -14, -0.286373955981183, -0.29756585143223624, -0.2849418036962145] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1936  total reward: -5257.83637537976
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6010546219766859, -0.590215940659218, -0.5622782789160996, -0.47151043350158167, -0.3814322102673902, -0.4122741779245729, -0.4586306689415322, -0.40465069665025105, -0.4115467909008824, -0.4644246215787405, -14, -0.41378630843251096, -0.42874047928361764, -14, -0.43347963494551967, -0.4066833705372754, -0.40057931279709735, -14, -0.4048435381619828, -0.41837426855644677, -0.40351779598503335] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1937  total reward: -5258.545976104255
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5651421557381701, -0.5838333317491784, -0.4417487729637795, -0.37272565945688646, -0.34646976697668763, -0.337399611751897, -0.37977404406867793, -0.3279045803635798, -0.33778857632944626, -0.37907345549082705, -14, -0.33637458364852235, -0.34590259083476677, -14, -0.36422144973771836, -0.33058864086962264, -0.33142778884461327, -14, -0.328846463527929, -0.33732188846992783, -0.32816851422692483] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1938  total reward: -5259.209822497354
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5694644634033026, -0.6007989180938395, -0.470542113614759, -0.39192431491960694, -0.3556912123887469, -0.3461557853161701, -0.40010133085622407, -0.3370548010886653, -0.341581247611627, -0.3718415061364332, -14, -0.34354210605070823, -0.34969760643217096, -14, -14, -0.3359999286740092, -0.3421059475096615, -14, -0.33666087050595117, -0.33962013178228684, -0.3359418127365023] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1939  total reward: -5259.986365396766
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7465251915141918, -0.7660155937639566, -0.6448253560356668, -0.5079891921667862, -0.46653028444837497, -0.4665153855239109, -0.5262811805250931, -0.4388899034352194, -0.4426025985567034, -0.4846111921472372, -14, -0.4491992947084831, -0.4559839505976862, -14, -14, -0.440861355661364, -0.452735760417824, -14, -0.44116432922392823, -0.44638098044384356, -0.44060108667452635] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1940  total reward: -5260.950312095496
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8908565924108972, -0.9199031162965752, -0.741818316723412, -0.6035653050854761, -0.5552098261998831, -0.5474992875420166, -0.6148045065282549, -0.5286901616309871, -0.5365778322274314, -0.5980644470043582, -14, -0.5363039072111476, -0.5523608723806251, -14, -0.5774934067836824, -0.5291171249288279, -0.5286561235869098, -14, -0.5267018481493375, -0.537693755413307, -0.5250567952948769] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1941  total reward: -5261.848624377786
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.37744032465437133, -0.3747523380905518, -0.47848317053746214, -0.4242670765300545, -0.3724360027061418, -0.37748684549221395, -0.3762585145442212, -0.4777810195962912, -0.3728560195557361, -0.39036919095221384, -14, -0.39007403126364265, -0.4107660055058363, -14, -0.5087544549470673, -0.37448495425289424, -0.3747556209255362, -14, -0.3757118895448182, -0.4000738176768207, -0.3732554869952575] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1942  total reward: -5263.028328016639
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2387806846606937, -1.1653951731242453, -1.1052921177770882, -0.9161405544640564, -0.7612826375510362, -0.8337431867633166, -0.9161297322031211, -0.8166822849604195, -0.8208482620598605, -0.8976951100098239, -14, -0.8265393356733647, -0.8557279131358202, -14, -0.8724170386422623, -0.8136102898593508, -0.7988792202402251, -14, -0.8099720557936481, -0.8378623876798797, -0.8072676361463226] argmax 4
Action chosen: switching off line 4
  Simulating cascading failure
  ok
timestep 1943  total reward: -5264.628180465697
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4172829386653225, -1.4717943257921813, -1.1384692516547068, -0.9708072066018496, -0.8869434956619218, -0.8575219085978412, -0.9852658555401276, -0.838674010839354, -0.8636480934586853, -0.9536737636064989, -14, -0.858287052863116, -0.887976913422052, -14, -0.9338744835887033, -0.8444974734606225, -0.8409319217849891, -14, -0.8419701021171802, -0.8665322044701165, -0.8385698115076168] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1944  total reward: -5266.399360413019
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.611303300448354, -1.667005780000736, -1.274263485854611, -1.0838828123759874, -0.9889660165891114, -0.9537920146322375, -1.103662848273453, -0.9248131707131153, -0.9626378241821903, -1.0703923544982579, -14, -0.9528881003772293, -0.9794589653195027, -14, -1.0216468793511062, -0.9384204210555588, -0.9309207822832553, -14, -0.9346316382119964, -0.9674106751568938, -0.9326101358143211] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1945  total reward: -5268.249539595065
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.545331112020314, -1.584494448062358, -1.3009682399411355, -1.0726337052352386, -0.9794469697422878, -0.9591925419553097, -1.1112917339516812, -0.9199087999310102, -0.9297057676173969, -0.9986817887788705, -14, -0.9441836358578225, -0.962117505957809, -14, -14, -0.9250468160203362, -0.9538069096393283, -14, -0.9274657176551832, -0.947077808165286, -0.9253660113320938] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1946  total reward: -5270.233721046292
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.8962841623002986, -1.8200279161764161, -1.541366767783118, -1.2034983191210444, -1.130708544187017, -1.1369168688392002, -1.2800802665648015, -1.08240552984732, -1.0771380466190037, -1.1637612546075877, -14, -1.0868343531522517, -1.1176072996088244, -14, -1.1457004801721702, -1.0725282882263163, -1.065451736590907, -14, -1.066841289968653, -1.0909189178643635, -1.0642726512974277] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1947  total reward: -5272.106105151735
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.334374640098743, -1.4518959403896161, -1.1058912448775333, -0.9299035955341222, -0.8496215280098837, -0.8304564909020407, -0.9196146871731651, -0.797132339886824, -0.8416275265485009, -0.9721457753983761, -14, -0.8293774691723501, -0.8531313692464692, -14, -0.8990273148876811, -0.8136931537901793, -0.8203150191161932, -14, -0.8098677529580924, -0.8304774136018512, -0.8081114541457682] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1948  total reward: -5273.843260174053
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6642255369752814, -1.6721734922370524, -1.3147723011579302, -1.0767097443950406, -0.9981926591144635, -0.9777588421370368, -1.1317837516414069, -0.938481257110629, -0.9453382506014989, -1.0495769592859767, -14, -0.9557113675969484, -0.9702821529217968, -14, -14, -0.9402233073004002, -0.9637430249372355, -14, -0.9416099536551175, -0.9514056759843014, -0.9400226824312344] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1949  total reward: -5275.531880306538
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2960069837960684, -1.3261184395280863, -1.046533278232235, -0.857348887112068, -0.7937947617532637, -0.7802733528205886, -0.8785687957745848, -0.7486142744148206, -0.7706732694013402, -0.8522834701932208, -14, -0.7664575005266563, -0.7910279271095667, -14, -0.823345650842239, -0.7552897276169779, -0.7511396285228399, -14, -0.7529696266326544, -0.7692369575750465, -0.750138875374292] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1950  total reward: -5276.932525556005
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1279026406681532, -1.0950592533189158, -0.9122475672521485, -0.7435398704772344, -0.6918310169585291, -0.6812900505333981, -0.7956509623473057, -0.6383802348659555, -0.6501976197148808, -0.6938405043540635, -14, -0.6661247046828864, -0.6803545824154166, -14, -14, -0.653680322538363, -0.6717622356762294, -14, -0.6535420212629975, -0.6572198670055371, -0.652030975051303] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1951  total reward: -5278.272673533345
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1698808679676416, -1.2391149264026349, -1.0025833599686653, -0.8191497642985582, -0.7419465111323279, -0.7287626466150067, -0.822079490491139, -0.7049441319435894, -0.7168930920010406, -0.8099186687829021, -14, -0.7184976367559591, -0.7389269311185231, -14, -0.7666232704162583, -0.7075729121817445, -0.7103591703842044, -14, -0.7033462589632035, -0.7178157997399037, -0.7017677424748486] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1952  total reward: -5279.788149639018
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.3995581660177496, -1.4218138329278185, -1.1033987244166334, -0.9363758777589191, -0.861985697629022, -0.8341155330023345, -0.9628368158517037, -0.8155679952619115, -0.8364084816669625, -0.8982661239127868, -14, -0.8347071407273581, -0.8653975510068597, -14, -0.903960742246384, -0.8180146545080351, -0.8140668441976555, -14, -0.817087253889741, -0.8472291873031604, -0.8137083631980921] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1953  total reward: -5281.5597382169235
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.6552124909173693, -1.661478143020386, -1.381573292934654, -1.1182100284398935, -1.019015672885406, -0.9993530685631996, -1.1586694571764824, -0.9580213835875226, -0.9791841286633352, -1.061363578023737, -14, -0.9810429037981634, -1.0097355629603724, -14, -1.0351820879627616, -0.9636423189385173, -0.9522060303844525, -14, -0.959734904255511, -0.9901258217136973, -0.9578802147072956] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1954  total reward: -5283.273041692426
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2059279678750219, -1.3369516905096241, -1.0860166319715798, -0.8386500738829192, -0.790899856855906, -0.8227214343896379, -0.8403784708669463, -0.7954123364612977, -0.7657461940826424, -14, -14, -0.7891994860311746, -0.8331234689082679, -14, -0.8445271595870774, -0.769141305044251, -0.7556985021795402, -14, -0.7683223385647847, -14, -0.7610974451182903] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1955  total reward: -5284.593423462557
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9450505221018551, -0.9837091294575121, -0.7884770167734194, -0.6522883189421347, -0.5966656174496404, -0.5843517080233309, -0.6608487513974332, -0.5610947574980873, -0.5835954019439934, -0.6400016828859031, -14, -0.579718107660148, -0.5998931642781307, -14, -0.6257407828707511, -0.5685892314726598, -0.5657098448808603, -14, -0.5666892822897968, -0.5843254033844048, -0.564683267951468] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1956  total reward: -5285.862751660297
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2377579403905359, -1.2302683142618545, -1.0134556706154085, -0.810667693478563, -0.7518746760101016, -0.74531970393414, -0.8575806271691914, -0.7088463714603763, -0.7149797744819016, -0.7702054622282752, -14, -0.7244232269817674, -0.7397959897166518, -14, -14, -0.7088768307220298, -0.7240909666427926, -14, -0.7102210538555643, -0.7206022303304188, -0.7082334402421733] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1957  total reward: -5287.446971258345
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.2932578893612328, -1.6385812273476024, -1.100874322939103, -0.9876616132581982, -0.8971332404876005, -0.8818617953187101, -0.9092432074396015, -0.8651111357979002, -0.8866862148135195, -1.2609638970319386, -14, -0.8828365153121257, -0.8825388927557265, -14, -14, -0.8595673338335863, -0.9993402565585525, -14, -0.8757590407623058, -0.8851717056914246, -0.8759861578053599] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1958  total reward: -5288.714098918008
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7077782808184385, -0.7320545311925153, -0.5720277686514047, -0.4724098923664625, -0.4324259008011904, -0.42153307521578354, -0.4826534337830914, -0.4121969019032891, -0.4133042386935912, -0.4468588187033924, -0.4204706586365321, -0.4171359958130676, -0.42387976882234857, -14, -14, -0.40794155318080344, -0.41967648622513126, -0.4130631873252735, -0.40879977322231015, -0.4129409241824623, -0.4075603258291242] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1959  total reward: -5289.481887487598
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.633554936083753, -0.7145478445404099, -0.47184692799402367, -0.4337690723316532, -0.3824212357529341, -0.3603739983923304, -0.4250636758292917, -0.3623845263574465, -0.42311544980799953, -0.40581850054339513, -0.3859378104668239, -0.37171219871635025, -0.3834364022138154, -14, -14, -0.36065869224393543, -0.36045905374061743, -0.3753496746735835, -0.36293114143325805, -0.3750380511976392, -0.3602282437614325] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1960  total reward: -5290.184175788214
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5908496195670817, -0.6612980080265771, -0.47819785887630245, -0.4205885086711166, -0.3644442664149676, -0.3449463263917648, -0.4134915134253251, -0.3451443599863448, -0.3908074405951799, -0.3769953847238846, -0.36591363055359605, -0.3518540457098327, -0.3621099586243722, -14, -14, -0.34392262812918256, -0.34199977194386305, -0.3568718681792851, -0.3441858962155013, -0.35884982835318785, -0.34206005685388907] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1961  total reward: -5290.766255860738
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.41985583152063644, -0.4227653357291753, -0.3291218369439614, -0.27603997818944526, -0.2547781467531722, -0.24718780448060745, -0.28729227932007895, -0.23844653295453397, -0.23902223086198404, -0.2699786601590293, -0.2451840847064614, -0.24780042080776213, -0.25851168799083907, -14, -14, -0.24041426565691454, -0.2367672399638093, -0.24090661788387457, -0.2416282269413695, -14, -0.24008030058020136] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1962  total reward: -5291.224959098957
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.38392915448257275, -0.38160075807305477, -0.3052868627662781, -0.25890277130270534, -0.23618671041986383, -0.22735315347877486, -0.2699784826112618, -0.22064349089805987, -0.22145879350844924, -0.23358158348219696, -0.22956656075433532, -0.22630032313459508, -0.23008186522385254, -14, -14, -0.22166228806063032, -0.22560588001104165, -0.2249951773396756, -0.2226367046044453, -0.2244399312281988, -0.22193599825508975] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1963  total reward: -5291.735763217783
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5282266721325489, -0.5150273181619505, -0.40288026267477633, -0.32786840239890125, -0.3084051236001831, -0.3030647088936596, -0.3385572038920027, -0.2857817091810048, -0.29727507094487954, -0.32426976784331835, -0.3028949360925493, -0.29636274637764104, -0.3030711962195328, -14, -0.3092257621130328, -0.2881060289618181, -0.2920359550026145, -0.295633583868648, -0.29108695181929695, -0.29535900345102467, -0.29016062792749064] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1964  total reward: -5292.359962962533
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6007007456929443, -0.5764281429687897, -0.46040478970173687, -0.38846669366109327, -0.3603596028909598, -0.34799788598052395, -0.41381615035648994, -0.3367948141007524, -0.33780225113881074, -0.3532021657693399, -0.35170088066379895, -0.3454089360314423, -0.3518469781156015, -14, -14, -0.3380436322522673, -0.34349387246347074, -0.34462206403127554, -0.3396583954875864, -0.3431056345097206, -0.3384180355702598] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1965  total reward: -5293.3256439163815
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9930709815797577, -1.191565076695772, -0.8252430757376168, -0.7244964280404914, -0.6530924567099168, -0.6357684176257669, -0.6736433066817635, -0.6209217416789835, -0.6506281571439043, -0.8494935821451335, -0.6299861363502853, -0.6351467887847182, -0.638460970919814, -14, -0.7045927330716629, -0.62943719291625, -0.6491056393983441, -0.624610813939307, -0.6290731929675452, -0.6292133654047372, -0.6288861397470726] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1966  total reward: -5294.444406535907
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8597714964269454, -0.8710885927490555, -0.673806682265494, -0.5779017399998638, -0.5286361830023809, -0.5080400406431509, -0.5969435293058398, -0.500115440516531, -0.5019277177972499, -0.529901461425655, -0.5168145426174302, -0.5092789866336123, -0.5179295212995804, -14, -14, -0.497766359052532, -0.5071606409028812, -0.5069787748151684, -0.4993377130697552, -0.5057393442438868, -0.4978408778462099] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1967  total reward: -5295.563208075294
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.087338647409647, -1.0596608341941076, -0.9025813327749511, -0.7074522021829897, -0.6595170720815154, -0.6612618478467098, -0.7559895231097913, -0.6145836100935956, -0.6199671601496356, -0.6690738610092811, -14, -0.6327254122899774, -0.6443730399057686, -14, -14, -0.6220009474742438, -0.6385929327942205, -14, -0.6222534949867884, -0.6296549278419208, -0.621035180334654] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1968  total reward: -5296.796399277197
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0251975281703822, -1.061264123592981, -0.8905247371991986, -0.7175742497560205, -0.654090821885206, -0.6473955983160535, -0.7288367518093369, -0.6215983512358451, -0.6335166250359142, -0.6926914793594561, -14, -0.6347395200777299, -0.6572776906163701, -14, -0.6822606662977295, -0.6231449472433112, -0.6227634541868347, -14, -0.6209857728473476, -0.639014044232351, -0.6186075918095069] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1969  total reward: -5298.340517704852
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.4311141457148886, -1.7993339082748336, -1.2272186902647855, -1.056046300852417, -0.9536495280230601, -0.9413450061886961, -0.9728502244995454, -0.9168468793459067, -0.9604673273619081, -1.410646027046151, -14, -0.9338098040518217, -0.9407192323505897, -14, -1.0321161572913669, -0.9279375013838717, -0.9890006064905199, -14, -0.9256132609291624, -0.9240797546033664, -0.9255108358442307] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1970  total reward: -5299.904085615642
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0948452430064393, -1.1209940840633636, -0.9275267609870981, -0.7414458260342017, -0.6840161307313615, -0.680599610085402, -0.7688294092211004, -0.6445262128434007, -0.6512264496123639, -0.7130031783387379, -14, -0.659832805770023, -0.6711847984902173, -14, -14, -0.6469602178119933, -0.6689305121838972, -14, -0.6479701921783789, -0.6566559662425577, -0.6467210314444358] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1971  total reward: -5301.197243675617
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.1189216466013399, -1.1121710761813275, -0.9541075339608506, -0.73145982849051, -0.6860738647414294, -0.7002124868584774, -0.7613018672546548, -0.6559666372346534, -0.6590858349817019, -0.734770857943178, -14, -0.6626003589351569, -0.68008474173881, -14, -0.7039985119652719, -0.6538019962792191, -0.6561643348766727, -14, -0.6499639840602007, -0.6628038152386745, -0.6486318471316211] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1972  total reward: -5302.343713713729
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8184769747717815, -0.8822011946906992, -0.7047068334055291, -0.5791594961601141, -0.5247720597554814, -0.5158571134182789, -0.5749596407293291, -0.49655937728390825, -0.5131093036425477, -0.5692451661251986, -14, -0.5088321382894264, -0.5226823737675874, -14, -0.5523125871169206, -0.501145393210979, -0.49930531337025685, -14, -0.49891775604452676, -0.5133222110157272, -0.49783819098043003] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1973  total reward: -5303.249549601316
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6714191336740509, -0.7341488705188705, -0.5516035071458686, -0.4778129364482321, -0.43105437703706373, -0.41596086627555307, -0.476637375121201, -0.4090743762853864, -0.415805309846137, -0.4701191299200756, -14, -0.4182307848969592, -0.42523391433484853, -14, -14, -0.40842469719325186, -0.4290467945288827, -14, -0.41013314133440204, -0.41296896966115837, -0.4092765103035688] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1974  total reward: -5304.132749336891
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8237035695851694, -0.8334319766261036, -0.6808318685172217, -0.5518547748593129, -0.5047848775663859, -0.4951305082029616, -0.5717125953420323, -0.4823384762279253, -0.48522900622812454, -0.504954964641063, -0.49734163604091997, -0.48541325014807496, -0.4937298426837848, -14, -14, -0.4746434275984614, -0.47761912459731615, -0.4866507776407153, -0.47614036544067345, -0.4841193103074299, -0.4747750383817028] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1975  total reward: -5305.121005938065
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8914439215787484, -0.8967162353807429, -0.7379714100829463, -0.5905010851213465, -0.5450934940426365, -0.5399270044506757, -0.6203903496228163, -0.5153953749816209, -0.5204154697764696, -0.5655756481657659, -14, -0.5249974333967422, -0.5359232458938652, -14, -14, -0.5137817246016633, -0.5254764450129358, -14, -0.5151041997616617, -0.5223656496295402, -0.5136131735749873] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1976  total reward: -5306.12901473664
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7981588742332136, -0.8792254173649919, -0.6762207882445671, -0.5784677258005069, -0.5200728217603889, -0.5044768812530984, -0.5741478889928134, -0.4946760958094336, -0.5031263567218316, -0.5641074288410425, -14, -0.5068583799233899, -0.5148771474480497, -14, -14, -0.49282931489195086, -0.5216211761944883, -14, -0.49512793974459446, -0.5007639318123696, -0.4943956250000294] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1977  total reward: -5307.17562350842
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9763313858458408, -0.9592996683565908, -0.7641165573819346, -0.6365753113411556, -0.5889804900462657, -0.5719354938552799, -0.6695401710614144, -0.5561486093853494, -0.5569066935072299, -0.5900098954735605, -0.5757778834849833, -0.5656569170438865, -0.5744488380541248, -14, -14, -0.5535632579201784, -0.5618939392325198, -0.5625723629723761, -0.5552194215306957, -0.5613176963356236, -0.5537794568887119] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1978  total reward: -5308.297475738834
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.0504889812313307, -0.9483107727738096, -0.823492313167162, -0.6331272546701692, -0.6050528072175491, -0.6154627275207649, -0.7083452336579488, -0.5632875442567101, -0.5665189711194828, -0.5999671105750749, -14, -0.5777013912967663, -0.5873892487212564, -14, -14, -0.5692946551924863, -0.5740789964778217, -14, -0.5691514044275233, -0.5796425860098883, -0.5682889724934554] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1979  total reward: -5309.31768805911
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7917141332118649, -0.8043506662815763, -0.6429543663136424, -0.5226391513804977, -0.4839298200237574, -0.4769496631642757, -0.5376923125732338, -0.4604601980953846, -0.4659937005270281, -0.518938412945179, -14, -0.4657317598323521, -0.47706313001356837, -14, -0.4990373543324813, -0.46055257955705464, -0.45759010147792556, -14, -0.4577213093813954, -0.46725019315758537, -0.45692477601938986] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1980  total reward: -5310.296950272739
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9528968483157032, -0.9525125654506779, -0.7532794007042154, -0.6383919998628722, -0.56287052044399, -0.5327370074689577, -0.6676693821525068, -0.517954271372817, -0.5436691274805643, -0.5570268951781798, -14, -0.5359605746197237, -0.5593066338260047, -14, -0.5179542713728171, -0.5208873035704991, -0.5172611218560178, -14, -0.5255346878372762, -0.5594940771479564, -0.5223374376097618] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1981  total reward: -5311.246225242118
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7009057932168609, -0.8048813632341166, -0.5981763682067602, -0.4832737866205379, -0.4493477545047124, -0.45311791100410287, -0.47557765441999356, -0.4478589962508706, -0.4335160342182792, -14, -14, -0.4474846528252016, -0.4715584696720339, -14, -0.46706657464741125, -0.4348668416840474, -0.42710276472769404, -14, -0.43595564273498577, -14, -0.43201384752330724] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1982  total reward: -5312.036532215789
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6563947497260745, -0.6882914664567921, -0.49287771735210584, -0.4451540826455222, -0.38979416285108437, -0.36455352312925826, -0.4519558744660101, -0.36156812927376136, -0.38320289749292313, -0.40964071618480086, -14, -0.37271917781969943, -0.38813517628627114, -14, -0.3615681292737614, -0.3628663797828588, -0.35995171670534476, -14, -0.36528285826550005, -0.38737001588381526, -0.36320420894255523] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1983  total reward: -5312.66819541729
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.46846543217591885, -0.4915056930880895, -0.36533015708629474, -0.30345355954557857, -0.28563480319998247, -0.281842435898994, -0.31804808914770616, -0.2783199165739772, -0.27482158831934667, -14, -14, -0.2820253193686476, -0.29668889604040705, -14, -0.2973599403995891, -0.2753779299954216, -0.2723390506575087, -14, -0.2738903963485999, -14, -0.2717114847960252] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1984  total reward: -5313.127232452625
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3056521837234925, -0.3479617124445538, -0.25277356393434985, -0.20974224308200973, -0.19505237354263857, -0.19408030271820964, -0.20760958635328955, -0.1931744439868659, -0.18876947813739134, -14, -14, -0.19433913122141352, -0.20442654545457964, -14, -0.20463695430941628, -0.18903261936295862, -0.18563141411764914, -14, -0.1888439822243179, -14, -0.18732555053985195] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1985  total reward: -5313.502236946659
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.31859734032818593, -0.33563799691915214, -0.2609605531172622, -0.2177411119960084, -0.19982198742505072, -0.19530140873050442, -0.2192459203442375, -0.19006622347061974, -0.1942901769879815, -0.21964868187553582, -14, -0.19371965299860283, -0.19874329809374588, -14, -0.20997077650808368, -0.1908436517338027, -0.1913755148473027, -14, -0.18969405526653052, -0.19423828571175766, -0.18937307991477575] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1986  total reward: -5313.853138656841
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.2721378246935484, -0.28310141721038545, -0.22524787375963876, -0.18454509561313578, -0.1704277077701407, -0.1680557672685113, -0.18709484946757488, -0.16218520963972022, -0.16586247647559124, -0.18543600451860884, -14, -0.16506730046531257, -0.16944942155706433, -14, -0.17983913849348412, -0.16272992254601093, -0.1617910954070477, -14, -0.1618572675768443, -0.164902813918506, -0.16152863026734865] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1987  total reward: -5314.195533579681
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.3157707532914777, -0.3287324483957551, -0.24322314888633445, -0.20926421136417994, -0.19168163455812226, -0.184250848361998, -0.21253486489239984, -0.17839532249530288, -0.1873973930793425, -0.2079996936717721, -14, -0.18488922784096373, -0.19061991756485275, -14, -0.197309840213777, -0.18199927588281054, -0.18072706031271507, -14, -0.18144811059753074, -0.18727317095775667, -0.1808662925726654] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1988  total reward: -5314.707717919324
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5938927855382476, -0.6450814728936117, -0.45180378442382774, -0.4016883019407283, -0.35581506753728515, -0.3360590890189538, -0.40695730418446757, -0.33542815716300034, -0.4323021143363615, -0.37839617296127204, -14, -0.34474252032697095, -0.3555156574855323, -14, -14, -0.33260970516499183, -0.33405926296754795, -14, -0.33671008121988255, -0.3592306718772414, -0.33378901714802595] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1989  total reward: -5315.418654418762
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6300219780766059, -0.6254080444531119, -0.5628197148493299, -0.4304469360280769, -0.39997289314510076, -0.4086195469609645, -0.4477993289574031, -0.37618092068932774, -0.37836558288350725, -0.39563458993114975, -0.3906885128340722, -0.38561124357925947, -0.39189453728084656, -14, -14, -0.37808358191082764, -0.3862829857616729, -0.38340094921842616, -0.37952003663912853, -0.38364096061868314, -0.37832679427359756] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1990  total reward: -5316.180794443146
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
  Simulating cascading failure
  ok
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
  Simulating cascading failure
  ok
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6413954050718705, -0.6855125801647249, -0.5270405068715295, -0.44853149527639335, -0.40718007917955834, -0.3945222090945063, -0.43894662388431444, -0.3834801002508106, -0.3969501292647302, -0.4321862552721915, -0.40369610369684783, -0.3946483008171154, -0.40434316082674204, -14, -0.4295384992333213, -0.38304841263486944, -0.3892225793697666, -0.3930978923371917, -0.38746262304588214, -0.39210502387179375, -0.3859591036934089] argmax 15
Action chosen: switching off line 15
  Simulating cascading failure
  ok
timestep 1991  total reward: -5317.051568656938
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.8475132240112659, -0.832021515157257, -0.7129695612284697, -0.5613056788044644, -0.5184018105650766, -0.5169734513976346, -0.5890419539987553, -0.4959168005366009, -0.4943071689448201, -0.5258146473434565, -14, -0.4994514818321634, -0.5133897624727088, -14, -0.5275343500085664, -0.4910437484818792, -0.4849414380063742, -14, -0.4885227026709842, -0.5003816318223725, -0.48772580115713754] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1992  total reward: -5318.071936695633
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.926654704826733, -0.9667196358949541, -0.7530037234725304, -0.5931702094503415, -0.5626094723170514, -0.5710156284881912, -0.6224004460904049, -0.5491131900481313, -0.5399129827654776, -14, -14, -0.551854520281725, -0.5787934174259953, -14, -0.5806944658635005, -0.542289078607307, -0.5366285834518034, -14, -0.5400754923830393, -14, -0.5354266006899784] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1993  total reward: -5319.077630985805
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.7590541634003252, -0.8450149833657071, -0.6384109005804688, -0.5349122037549444, -0.49162821284821584, -0.48490231731972183, -0.539774878313211, -0.4813141789793935, -0.4793288382203849, -14, -14, -0.48691503690229393, -0.5109061947021108, -14, -0.5274417880393181, -0.4763539653978891, -0.4720012710619274, -14, -0.4738870226346291, -14, -0.47026768948110836] argmax 20
Action chosen: no action
  Simulating cascading failure
  ok
timestep 1994  total reward: -5320.072121392517
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.9035719976737365, -0.951571754401235, -0.7306224123535952, -0.5825766346171356, -0.5506136729513542, -0.5549482497475896, -0.6078637418957636, -0.5377441866481748, -0.5280115230419321, -14, -14, -0.543505246166891, -0.571497942085255, -14, -0.5662156140932767, -0.530853691322027, -0.5240027561501949, -14, -0.5284799845249833, -14, -0.5242227172318938] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1995  total reward: -5321.496270540942
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-1.9566312795846084, -1.3484114569408499, -1.1742487238687087, -0.9008245702465058, -0.940046954554157, -1.049415862533675, -1.1045657887827207, -0.9504853295171363, -0.9024966911796998, -0.9063786569605465, -14, -0.9133318242971536, -0.9349933426958664, -14, -0.9686479397817904, -0.9035496689692453, -0.8895198418393473, -14, -0.9020305479426185, -0.9272809793827498, -0.9001463922731626] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1996  total reward: -5322.781371821916
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.648572177101002, -0.7071717004919151, -0.5452517371866173, -0.4385734779385179, -0.41285102746561797, -0.4172948822028468, -0.4455491690745639, -0.41097384464682857, -0.39843817880008797, -14, -14, -0.41087516392950696, -0.4320012000690624, -14, -0.43681394811615987, -0.3998777238881817, -0.3943698163313754, -14, -0.39861891623573853, -14, -0.3955814391355054] argmax 16
Action chosen: switching off line 16
  Simulating cascading failure
  ok
timestep 1997  total reward: -5323.520377161705
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5765890225903479, -0.6257647548627817, -0.47938207117705095, -0.4017305357467448, -0.36361863129420374, -0.3540816951506074, -0.39800450135739945, -0.34269041888060625, -0.3544693175579153, -0.40885128175487556, -14, -0.3526226048917488, -0.36239679212598985, -14, -0.37617753220650846, -0.34727509936095996, -0.35079714977521614, -14, -0.3454500149061118, -0.3529133933534456, -0.3446355234583748] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1998  total reward: -5324.186576884278
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.5543327757355737, -0.5648040362607346, -0.45155552367957186, -0.3675809730047107, -0.3419193514227634, -0.3379794832587635, -0.3820665087918671, -0.32150841495538673, -0.324903248166381, -0.3604241248555172, -14, -0.33082007829924825, -0.3365773902591417, -14, -14, -0.3230620946360538, -0.34122734519610876, -14, -0.3240678914594762, -0.32754868135488274, -0.3235093036913619] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 1999  total reward: -5324.873743610189
 Simulation with line 0 switched off
  Simulating cascading failure
  ok
 Simulation with line 1 switched off
  Simulating cascading failure
  ok
 Simulation with line 2 switched off
  Simulating cascading failure
  ok
 Simulation with line 3 switched off
  Simulating cascading failure
  ok
 Simulation with line 4 switched off
  Simulating cascading failure
  ok
 Simulation with line 5 switched off
  Simulating cascading failure
  ok
 Simulation with line 6 switched off
  Simulating cascading failure
  ok
 Simulation with line 7 switched off
  Simulating cascading failure
  ok
 Simulation with line 8 switched off
  Simulating cascading failure
  ok
 Simulation with line 9 switched off
  Simulating cascading failure
  ok
 Simulation with line 10 switched off
 Simulation with line 11 switched off
  Simulating cascading failure
  ok
 Simulation with line 12 switched off
  Simulating cascading failure
  ok
 Simulation with line 13 switched off
 Simulation with line 14 switched off
  Simulating cascading failure
  ok
 Simulation with line 15 switched off
  Simulating cascading failure
  ok
 Simulation with line 16 switched off
  Simulating cascading failure
  ok
 Simulation with line 17 switched off
 Simulation with line 18 switched off
  Simulating cascading failure
  ok
 Simulation with line 19 switched off
  Simulating cascading failure
  ok
 Simulation with no action
  Simulating cascading failure
  ok
rewards [-0.6265374653234261, -0.6654555764731788, -0.4970116229292041, -0.4222008346120909, -0.3863627422015104, -0.3741463550120255, -0.4238797088687755, -0.3651471976829501, -0.3751783084240531, -0.42954242111245455, -14, -0.37440986207763566, -0.3847385710568888, -14, -0.4004649901334502, -0.3685177810456038, -0.3706663379585085, -14, -0.3664511405693689, -0.37283415744777193, -0.3656583109567827] argmax 7
Action chosen: switching off line 7
  Simulating cascading failure
  ok
timestep 2000  total reward: -5325.6611312754485

Plotting some stats

In [40]:
from scipy.stats import norm  # Used for best fitting line for histograms
import matplotlib.mlab as mlab
import matplotlib.gridspec as gridspec


def plot_multiple_curves(rewards, names, title, ylabel):
    plt.figure(figsize=(15, 10))
    colors = ['r', 'g', 'b', 'm', 'y', 'c']
    for r, (reward, name) in enumerate(zip(rewards, names)):
        plt.plot(np.arange(len(reward)), reward, color=colors[r], label=name)
        plt.xlabel('timestep')
        plt.ylabel(ylabel)
    plt.legend(loc='best')
    plt.xlim((1, len(rewards[0])))
    plt.title(title)
    
def plot_multiple_histograms(rewards, names, title, fitting_curves=True):
    colors = ['r', 'g', 'b', 'm', 'y', 'c']
    
    f, axes = plt.subplots(len(rewards), 1, sharex=True, sharey=True, figsize=(15, 10))
    
    gs1 = gridspec.GridSpec(len(rewards), 1)
    gs1.update(wspace=0.025, hspace=0.005)

    for r, (reward, name) in enumerate(zip(rewards, names)):
        ax = axes[r]
        (mu, sigma) = norm.fit(reward)
        n, bins, patches = ax.hist(reward, 100, range=(min([np.min(r) for r in rewards]), max([np.max(r) for r in rewards])), 
                                   density=True, facecolor=colors[r], alpha=0.75, label=name)
        if fitting_curves:
            y = mlab.normpdf(bins, mu, sigma)
            l = ax.plot(bins, y, colors[r]+'--', linewidth=2)
        #ax.set_xlabel('timestep')
        ax.set_ylabel('density')
        ax.legend()
        if r == len(rewards)-1:
            ax.set_xlabel('timestep reward')
    plt.subplots_adjust(wspace=0, hspace=0)
In [41]:
#plot_multiple_curves((rewards_do_nothing, rewards_random_switchoff, rewards_random_node_split, rewards_greedy_switchoff), 
#                     ('do-nothing', 'random switch-off', 'random node-splitting', 'treesearch switch off'),
#                     title='Reward by timestep given policies',
#                     ylabel='timestep reward')
In [42]:
plot_multiple_curves((rewards_do_nothing, rewards_random_switchoff, rewards_greedy_switchoff), 
                     ('do-nothing', 'random switch-off', 'tree search switch off'),
                     title='Reward by timestep given policies',
                     ylabel='timestep reward')
In [43]:
#plot_multiple_histograms((rewards_do_nothing, rewards_random_switchoff, rewards_random_node_split, rewards_greedy_switchoff), 
#                         ('do-nothing', 'random switch-off', 'random node-splitting', 'treesearch switch off'),
#                         title='Reward by timestep given policies',
#                         fitting_curves=True)
In [44]:
plot_multiple_histograms((rewards_do_nothing, rewards_random_switchoff, rewards_greedy_switchoff), 
                         ('do-nothing', 'random switch-off', 'tree search switch off'),
                         title='Reward by timestep given policies',
                         fitting_curves=False)
In [45]:
def clean_rewards(rewards):
    # Discard connexity -5 rewards, to plot the rewards when the action did not lead to connexity issues
    return rewards[rewards > env.connexity_exception_reward]

clean_rewards_do_nothing = clean_rewards(rewards_do_nothing)
clean_rewards_random_switchoff = clean_rewards(rewards_random_switchoff)
clean_rewards_greedy_switchoff = clean_rewards(rewards_greedy_switchoff)

plot_multiple_histograms((clean_rewards_do_nothing, 
                          clean_rewards_random_switchoff,
                          clean_rewards_greedy_switchoff), 
                         ('do-nothing', 
                          'random switch-off',
                          'tree search switch off'),
                         title='Reward by timestep given policies',
                         fitting_curves=True)
In [46]:
from itertools import accumulate
plot_multiple_curves((list(accumulate(rewards_do_nothing)), 
                      list(accumulate(rewards_random_switchoff)),
                      list(accumulate(rewards_greedy_switchoff)),), 
                     ('do-nothing policy', 
                      'random switch-off policy',
                      'tree search switch off'),
                     title='Cumulative reward given policies',
                     ylabel='Cumulative reward')
In [22]:
def clean_rewards(rewards):
    # Discard connexity -5 rewards, to plot the rewards when the action did not lead to connexity issues
    return rewards[rewards > -7]

clean_rewards_do_nothing = clean_rewards(rewards_do_nothing)
clean_rewards_random_switchoff = clean_rewards(rewards_random_switchoff)
clean_rewards_random_node_split = clean_rewards(rewards_random_node_split)
clean_rewards_greedy_switchoff = clean_rewards(rewards_greedy_switchoff)

plot_multiple_histograms((clean_rewards_do_nothing, 
                          clean_rewards_random_switchoff, 
                          clean_rewards_random_node_split,
                          clean_rewards_greedy_switchoff), 
                         ('do-nothing', 
                          'random switch-off', 
                          'random node-splitting',
                          'treesearch switch off'),
                         title='Reward by timestep given policies',
                        fitting_curves=False)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-22-3ce78c8a7df4> in <module>()
      5 clean_rewards_do_nothing = clean_rewards(rewards_do_nothing)
      6 clean_rewards_random_switchoff = clean_rewards(rewards_random_switchoff)
----> 7 clean_rewards_random_node_split = clean_rewards(rewards_random_node_split)
      8 clean_rewards_greedy_switchoff = clean_rewards(rewards_greedy_switchoff)
      9 

NameError: name 'rewards_random_node_split' is not defined
In [ ]:
from itertools import accumulate
plot_multiple_curves((list(accumulate(rewards_do_nothing)), 
                      list(accumulate(rewards_random_switchoff)), 
                      list(accumulate(rewards_random_node_split)), 
                      list(accumulate(rewards_greedy_switchoff)),), 
                     ('do-nothing policy', 
                      'random switch-off policy', 
                      'random node-splitting policy',
                      'treesearch switch off'),
                     title='Cumulative reward given policies',
                     ylabel='Cumulative reward')
In [ ]: